The selfie trap: A novel camera trap design for accurate small mammal identification

Camera traps are a popular tool for monitoring wildlife though they can fail to capture enough morphological detail for accurate small mammal species identification. Camera trapping small mammals is often limited by the inability of camera models to: (i) record at close distances; and (ii) provide standardised photos. This study aims to provide a camera trapping method that captures standardised images of the faces of small mammals for accurate species identification, with further potential for individual identification. A novel camera trap design coined the ‘selfie trap’ was developed. The selfie trap is a camera contained within an enclosed PVC pipe with a modified lens that produces standardised close images of small mammal species encountered in this study, including: Brown Antechinus (Antechinus stuartii), Bush Rat (Rattus fuscipes) and Sugar Glider (Petaurus breviceps). Individual identification was tested on the common arboreal Sugar Glider. Five individual Sugar Gliders were identified based on unique head stripe pelage. The selfie trap is an accurate camera trapping method for capturing detailed and standardised images of small mammal species. The design described may be useful for wildlife management as a reliable method for surveying small mammal species. However, intraspecies individual identification using the selfie trap requires further testing.     

Accuracy of identifications of mammal species from camera trap images: A northern Australian case study

Camera traps are a powerful and increasingly popular tool for mammal research, but like all survey methods, they have limitations. Identifying animal species from images is a critical component of camera trap studies, yet while researchers recognize constraints with experimental design or camera technology, image misidentification is still not well understood. We evaluated the effects of a species’ attributes (body mass and distinctiveness) and individual observer variables (experience and confidence) on the accuracy of mammal identifications from camera trap images. We conducted an Internet‐based survey containing 20 questions about observer experience and 60 camera trap images to identify. Images were sourced from surveys in northern Australia and included 25 species, ranging in body mass from the delicate mouse (Pseudomys delicatulus, 10 g) to the agile wallaby (Macropus agilis, >10 kg). There was a weak relationship between the accuracy of mammal identifications and observer experience. However, accuracy was highest (100%) for distinctive species (e.g. Short‐beaked echidna [Tachyglossus aculeatus]) and lowest (36%) for superficially non‐distinctive mammals (e.g. rodents like the Pale field‐rat [Rattus tunneyi]). There was a positive relationship between the accuracy of identifications and body mass. Participant confidence was highest for large and distinctive mammals, but was not related to participant experience level. Identifications made with greater confidence were more likely to be accurate. Unreliability in identifications of mammal species is a significant limitation to camera trap studies, particularly where small mammals are the focus, or where similar‐looking species co‐occur. Integration of camera traps with conventional survey techniques (e.g. live‐trapping), use of a reference library or computer‐automated programs are likely to aid positive identifications, while employing a confidence rating system and/or multiple observers may lead to a collection of more robust data. Although our study focussed on Australian species, our findings apply to camera trap studies globally.     

Animal Scanner: Software for classifying humans,animals, and empty frames in camera trap images

Camera traps are a popular tool to sample animal populations because they are noninvasive, detect a variety of species, and can record many thousands of animal detections per deployment. Cameras are typically set to take bursts of multiple photographs for each detection and are deployed in arrays of dozens or hundreds of sites, often resulting in millions of photographs per study. The task of converting photographs to animal detection records from such large image collections is daunting, and made worse by situations that generate copious empty pictures from false triggers (e.g., camera malfunction or moving vegetation) or pictures of humans. We developed computer vision algorithms to detect and classify moving objects to aid the first step of camera trap image filtering—separating the animal detections from the empty frames and pictures of humans. Our new work couples foreground object segmentation through background subtraction with deep learning classification to provide a fast and accurate scheme for human–animal detection. We provide these programs as both Matlab GUI and command prompt developed with C++. The software reads folders of camera trap images and outputs images annotated with bounding boxes around moving objects and a text file summary of results. This software maintains high accuracy while reducing the execution time by 14 times. It takes about 6 seconds to process a sequence of ten frames (on a 2.6 GHZ CPU computer). For those cameras with excessive empty frames due to camera malfunction or blowing vegetation automatically removes 54% of the false‐triggers sequences without influencing the human/animal sequences. We achieve 99.58% on image‐level empty versus object classification of Serengeti dataset. We offer the first computer vision tool for processing camera trap images providing substantial time savings for processing large image datasets, thus improving our ability to monitor wildlife across large scales with camera traps.     

An approach to rapid processing of camera trap images with minimal human input

1. Camera traps have become an extensively utilized tool in ecological research, but the manual processing of images created by a network of camera traps rapidly becomes an overwhelming task, even for small camera trap studies.
2. We used transfer learning to create convolutional neural network (CNN) models for identification and classification. By utilizing a small dataset with an average of 275 labeled images per species class, the model was able to distinguish between species and remove false triggers.
3. We trained the model to detect 17 object classes with individual species identification, reaching an accuracy up to 92% and an average F1 score of 85%. Previous studies have suggested the need for thousands of images of each object class to reach results comparable to those achieved by human observers; however, we show that such accuracy can be achieved with fewer images.
4. With transfer learning and an ongoing camera trap study, a deep learning model can be successfully created by a small camera trap study. A generalizable model produced from an unbalanced class set can be utilized to extract trap events that can later be confirmed by human processors.

     

The efficiency of two widely used commercial live-traps to develop monitoring protocols for small mammal biodiversity

Biodiversity monitoring programs have been implemented worldwide as a source of information on ecosystem functioning. However, controversy concerning the indicators that should be monitored, and the development of adequate monitoring protocols for multi-species communities still hamper such implementation, especially in the case of small mammals. We analyze differences in the efficiency of the two most widely used commercial traps (Longworth and Sherman) working simultaneously in eight different mountain habitats in Andorra country (NE Iberia) as a first step for establishing standardized sampling protocols for species-rich small mammal communities. From summer 2008 to fall 2010 (six sampling occasions) we captured a total of 728 small mammal individuals (1445 including recaptures) of 13 species (12 in Longworth and 11 in Sherman, 10 species shared). Despite some specific biases (underestimation of two large species by Longworth traps and underestimation of one small species by Sherman traps), estimates of community parameters and similarity indexes, sampling efficiency (number of small mammals trapped), detectability, mean weight, and sex-ratio of the most abundant species, were similar for both sampling methods. Our results suggested that both trap models could be used interchangeably – without relevant biases – in small mammal community assessments where large species are infrequent. Focussing monitoring programs on highly detectable small mammal species (common species) would allow the establishment of robust monitoring programs aimed at reducing the time invested and economic costs.     

Human vs. machine: Detecting wildlife in camera trap images

As the capacity to collect and store large amounts of data expands, identifying and evaluating strategies to efficiently convert raw data into meaningful information is increasingly necessary. Across disciplines, this data processing task has become a significant challenge, delaying progress and actionable insights. In ecology, the growing use of camera traps (i.e., remotely triggered cameras) to collect information on wildlife has led to an enormous volume of raw data (i.e., images) in need of review and annotation. To expedite camera trap image processing, many have turned to the field of artificial intelligence (AI) and use machine learning models to automate tasks such as detecting and classifying wildlife in images. To contribute understanding of the utility of AI tools for processing wildlife camera trap images, we evaluated the performance of a state-of-the-art computer vision model developed by Microsoft AI for Earth named MegaDetector using data from an ongoing camera trap study in Arctic Alaska, USA. Compared to image labels determined by manual human review, we found MegaDetector reliably determined the presence or absence of wildlife in images generated by motion detection camera settings (≥94.6% accuracy), however, performance was substantially poorer for images collected with time-lapse camera settings (≤61.6% accuracy). By examining time-lapse images where MegaDetector failed to detect wildlife, we gained practical insights into animal size and distance detection limits and discuss how those may impact the performance of MegaDetector in other systems. We anticipate our findings will stimulate critical thinking about the tradeoffs of using automated AI tools or manual human review to process camera trap images and help to inform effective implementation of study designs.     

An automatic method for removing empty camera trap images using ensemble learning

Camera traps often produce massive images, and empty images that do not contain animals are usually overwhelming. Deep learning is a machine‐learning algorithm and widely used to identify empty camera trap images automatically. Existing methods with high accuracy are based on millions of training samples (images) and require a lot of time and personnel costs to label the training samples manually. Reducing the number of training samples can save the cost of manually labeling images. However, the deep learning models based on a small dataset produce a large omission error of animal images that many animal images tend to be identified as empty images, which may lead to loss of the opportunities of discovering and observing species. Therefore, it is still a challenge to build the DCNN model with small errors on a small dataset. Using deep convolutional neural networks and a small‐size dataset, we proposed an ensemble learning approach based on conservative strategies to identify and remove empty images automatically. Furthermore, we proposed three automatic identifying schemes of empty images for users who accept different omission errors of animal images. Our experimental results showed that these three schemes automatically identified and removed 50.78%, 58.48%, and 77.51% of the empty images in the dataset when the omission errors were 0.70%, 1.13%, and 2.54%, respectively. The analysis showed that using our scheme to automatically identify empty images did not omit species information. It only slightly changed the frequency of species occurrence. When only a small dataset was available, our approach provided an alternative to users to automatically identify and remove empty images, which can significantly reduce the time and personnel costs required to manually remove empty images. The cost savings were comparable to the percentage of empty images removed by models.     

Comparing motion capture cameras versus human observer monitoring of mammal movement through fence gaps: a case study from Kenya

Monitoring the movement and distribution of wildlife is a critical tool of an adaptive management framework for wildlife conservation. We installed motion‐triggered cameras to capture the movement of mammals through two purpose‐built migration gaps in an otherwise fenced conservancy in northern Kenya. We compared the results to data gathered over the same time period (1 Jan 2011–31 Dec 2012) by the human observers monitoring mammal tracks left at the same fence gaps in a sandy loam detection strip. The camera traps detected more crossing events, more species and more individuals of each species per crossing event than did the human track observers. We tested for volume detection differences between methods for the five most common species crossing each gap and found that all detection rates were heavily weighted towards the camera‐trap method. We review some of the discrepancies between the methods and conclude that although the camera traps record more data, the management of that data can be time‐consuming and ill‐suited to some time‐sensitive decision‐making. We also discuss the importance of daily track monitoring for adaptive management conservation and community security.     

中国的野生动物红外相机监测需要统一的标准

采用及时、可靠的方法对物种开展有效监测是生物多样性保护的基础。红外相机技术可以获得兽类物种的影像、元数据和分布信息, 是监测生物多样性的有效途径。这项技术在野外便于部署, 规程易于标准化, 可提供野生动物凭证标本(影像)以及物种拍摄位置、拍摄日期与时间、拍摄细节(相机型号等)等附属信息。这些特性使得我们可以积累数以百万计的影像资料和野生动物监测数据。在中国, 红外相机技术已得到广泛应用, 众多机构正在使用红外相机采集并存储野生动物影像以及相关联的元数据。目前, 亟需对红外相机元数据结构进行标准化, 以促进不同机构之间以及与外部保护团体之间的数据共享。迄今全球已建立有数个国际数据共享平台, 例如Wildlife Insights, 但他们离不开与中国的合作, 以有效追踪全球可持续发展的进程。达成这样的合作需要3个基础: 共同的数据标准、数据共享协议和数据禁用政策。我们倡议, 中国保护领域的政府主管部门、机构团体一起合作, 共同制定在国内单位之间以及与国际机构之间共享监测数据的政策、机制与途径。     

利用红外相机对四川白水河国家级自然保护区鸟兽资源的初步调查

2017年5月至2018年5月, 我们在四川白水河国家级自然保护区内设置红外相机对地面活动鸟兽进行了初步调查。布设在24个位点的24台相机累计工作3,832天, 共获得可识别物种的独立有效照片535张。经鉴定, 兽类有4目10科17种, 鸟类有2目4科10种。其中, 国家I级重点保护野生动物5种, 国家II级重点保护野生动物8种, 中国豪猪(Hystrix hodgsoni)、宝兴歌鸫(Turdus mupinensis)和黑顶噪鹛(Trochalopteron affine)为保护区新记录种, 而大熊猫(Ailuropoda melanoleuca)为汶川地震后首次拍到。兽类中, 花面狸(Paguma larvata)、黄喉貂(Martes flavigula)和中华斑羚(Naemorhedus griseus) 3种动物的独立有效照片总数占全部兽类独立有效照片数的50.2%。鸟类中, 血雉(Ithaginis cruentus)和红腹角雉(Tragopan temminckii)的独立有效照片总数占全部鸟类独立有效照片数的91.6%。本研究为白水河国家级自然保护区野生动物资源管理和保护提供了参考依据。     

Design patterns for wildlife‐related camera trap image analysis

This paper describes and explains design patterns for software that supports how analysts can efficiently inspect and classify camera trap images for wildlife‐related ecological attributes. Broadly speaking, a design pattern identifies a commonly occurring problem and a general reusable design approach to solve that problem. A developer can then use that design approach to create a specific software solution appropriate to the particular situation under consideration. In particular, design patterns for camera trap image analysis by wildlife biologists address solutions to commonly occurring problems they face while inspecting a large number of images and entering ecological data describing image attributes. We developed design patterns for image classification based on our understanding of biologists' needs that we acquired over 8 years during development and application of the freely available Timelapse image analysis system. For each design pattern presented, we describe the problem, a design approach that solves that problem, and a concrete example of how Timelapse addresses the design pattern. Our design patterns offer both general and specific solutions related to: maintaining data consistency, efficiencies in image inspection, methods for navigating between images, efficiencies in data entry including highly repetitious data entry, and sorting and filtering image into sequences, episodes, and subsets. These design patterns can inform the design of other camera trap systems and can help biologists assess how competing software products address their project‐specific needs along with determining an efficient workflow.     

Automatically detecting the wild giant panda using deep learning with context and species distribution model

The giant panda is a flagship species in ecological conservation. The infrared camera trap is an effective tool for monitoring the giant panda. Images captured by infrared camera traps must be accurately recognized before further statistical analyses can be implemented. Previous research has demonstrated that spatiotemporal and positional contextual information and the species distribution model (SDM) can improve image detection accuracy, especially for difficult-to-see images. Difficult-to-see images include those in which individual animals are only partially observed and it is challenging for the model to detect those individuals. By utilizing the attention mechanism, we developed a unique method based on deep learning that incorporates object detection, contextual information, and the SDM to achieve better detection performance in difficult-to-see images. We obtained 1169 images of the wild giant panda and divided them into a training set and a test set in a 4:1 ratio. Model assessment metrics showed that our proposed model achieved an overall performance of 98.1% in mAP_0.5 and 82.9% in recall on difficult-to-see images. Our research demonstrated that the fine-grained multimodal-fusing method applied to monitoring giant pandas in the wild can better detect the difficult-to-see panda images to enhance the wildlife monitoring system.     

探讨我国森林野生动物红外相机监测规范

野生动物多样性是生物多样性监测与保护管理评价的关键指标, 因此对野生动物进行长期监测是中国森林生物多样性监测网络(CForBio)等大尺度生物多样性监测研究计划的一个重要组成部分。2011年以来, CForBio网络陆续在多个森林动态监测样地开展以红外相机来监测野生动物多样性。随着我国野生动物红外相机监测网络的初步形成, 亟待建立和执行基于红外相机技术的统一监测规范。基于3年来在我国森林动态监测样地红外相机监测的进展情况, 以及热带生态评价与监测网络针对陆生脊椎动物(兽类和鸟类)所提出的红外相机监测规范, 本文从监测规范和监测注意事项等方面探讨了我国森林野生动物红外相机监测的现状和未来。     

Motion vectors and deep neural networks for video camera traps

Commercial camera traps are usually triggered by a Passive Infra-Red (PIR) motion sensor necessitating a delay between triggering and the image being captured. This often seriously limits the ability to record images of small and fast moving animals. It also results in many “empty” images, e.g., owing to moving foliage against a background of different temperature. In this paper we detail a new triggering mechanism based solely on the camera sensor. This is intended for use by citizen scientists and for deployment on an affordable, compact, low-power Raspberry Pi computer (RPi). Our system introduces a video frame filtering pipeline consisting of movement and image-based processing. This makes use of Machine Learning (ML) feasible on a live camera stream on an RPi. We describe our free and open-source software implementation of the system; introduce a suitable ecology efficiency measure that mediates between specificity and recall; provide ground-truth for a video clip collection from camera traps; and evaluate the effectiveness of our system thoroughly. Overall, our video camera trap turns out to be robust and effective.     

红外相机技术在我国野生动物监测中的应用: 问题与限制

红外相机(camera traps)作为对野生动物进行“非损伤”性采样的技术, 已成为研究动物多样性、种群生态学及行为学的常用手段之一。其发展和普及为中国野生动物多样性和物种保育研究带来了诸多机会。如今, 国内大多数自然保护区都在运用红外相机技术开展物种监测工作。本文结合20年来已发表的相关研究, 从内容、实验设计以及发展趋势方面, 总结了目前红外相机技术在应用过程中出现的共性问题; 并就相机对动物的干扰性、影像识别、研究的适用范围及安全保障四个方面, 对该项技术在实践中存在的限制进行了探讨。最后结合红外相机技术未来的发展方向, 提出了建立技术规范、数据集成和共享、影像数据版权维护、提高监测效率等问题。     

Take Only Photographs,Leave Only Footprints: Novel Applications of Non-Invasive Survey Methods for Rapid Detection of Small,Arboreal Animals

The development of appropriate wildlife survey techniques is essential to promote effective and efficient monitoring of species of conservation concern. Here, we demonstrate the utility of two rapid-assessment, non-invasive methods to detect the presence of elusive, small, arboreal animals. We use the hazel dormouse, Muscardinus avellanarius, a rodent of conservation concern, as our focal species. Prevailing hazel dormouse survey methods are prolonged (often taking months to years to detect dormice), dependent on season and habitat, and/or have low detection rates. Alternatives would be of great use to ecologists who undertake dormouse surveys, especially those assessing the need for mitigation measures, as legally required for building development projects. Camera traps and footprint tracking are well-established tools for monitoring elusive large terrestrial mammals, but are rarely used for small species such as rodents, or in arboreal habitats. In trials of these adapted methods, hazel dormice visited bait stations and were successfully detected by both camera traps and tracking equipment at each of two woodland study sites, within days to weeks of installation. Camera trap images and footprints were of adequate quality to allow discrimination between two sympatric small mammal species (hazel dormouse and wood mouse, Apodemus sylvaticus). We discuss the relative merits of these methods with respect to research aims, funds, time available and habitat.     

Mammal Diversity and Conservation in a Secondary Forest in Peninsular Malaysia

A comprehensive survey on large mammal diversity from a disturbed forest in Peninsular Malaysia has been carried out for over a period of 21 months. A total of 24 camera traps which accumulated to 5972 trap days. A total of 33 species 27 genera and 15 families of mammals were recorded via camera trapping and observations. The use of camera traps provides detailed information on diversity of some cryptic and secretive mammals. Secondary forest may support a wide diversity of mammals at a stable condition where intrusion, excision and fragmentation are reduced or avoided. The threats to mammals in the study are also discussed.     

A camera trap assessment of terrestrial vertebrates in Bwindi Impenetrable National Park,Uganda

We placed camera traps for a month at sixty locations in Bwindi Impenetrable National Park to determine the species composition and distribution of medium‐to‐large terrestrial vertebrates. A total of 15912 images were recorded from 1800 camera trap days. These provided a total of 625 and 338 camera events when filtered by hour and day, respectively. Twenty mammal species were recorded from 594 and 314 camera events by hour and day, respectively. Four bird species were recorded from 31 and 24 camera events by hour and day, respectively. The African golden cat Profelis aurata Temminck was recorded from 27 and nineteen camera events by hour and day, respectively. The black‐fronted duiker Cephalophus nigrifrons Gray was most frequently photographed with 179 and 65 camera events by hour and day, respectively. Analyses reveal two species possessed a significantly interior‐biased distribution. One species showed an edge‐biased pattern. Five species were detected to have significantly biased altitudinal distributions with higher elevations. Distance to park edge and elevation can significantly influence species distribution. The selective use of the park limits the area that each species utilizes, with implications for maximum population sizes and viability. Our observations provide a baseline for long‐term terrestrial vertebrate monitoring in Bwindi.     

Optimising Camera Traps for Monitoring Small Mammals

Practical techniques are required to monitor invasive animals, which are often cryptic and occur at low density. Camera traps have potential for this purpose, but may have problems detecting and identifying small species. A further challenge is how to standardise the size of each camera’s field of view so capture rates are comparable between different places and times. We investigated the optimal specifications for a low-cost camera trap for small mammals. The factors tested were 1) trigger speed, 2) passive infrared vs. microwave sensor, 3) white vs. infrared flash, and 4) still photographs vs. video. We also tested a new approach to standardise each camera’s field of view. We compared the success rates of four camera trap designs in detecting and taking recognisable photographs of captive stoats ( Mustela erminea ), feral cats (Felis catus) and hedgehogs ( Erinaceus europaeus ). Trigger speeds of 0.2–2.1 s captured photographs of all three target species unless the animal was running at high speed. The camera with a microwave sensor was prone to false triggers, and often failed to trigger when an animal moved in front of it. A white flash produced photographs that were more readily identified to species than those obtained under infrared light. However, a white flash may be more likely to frighten target animals, potentially affecting detection probabilities. Video footage achieved similar success rates to still cameras but required more processing time and computer memory. Placing two camera traps side by side achieved a higher success rate than using a single camera. Camera traps show considerable promise for monitoring invasive mammal control operations. Further research should address how best to standardise the size of each camera’s field of view, maximise the probability that an animal encountering a camera trap will be detected, and eliminate visible or audible cues emitted by camera traps.     

Critical evaluation of a long-term, locally-based wildlife monitoring program in West Africa

Effective monitoring programs are required to understand and mitigate biodiversity declines, particularly in tropical ecosystems where conservation conflicts are severe yet ecological data are scarce. “Locally-based” monitoring has been advanced as an approach to improve biodiversity monitoring in developing countries, but the accuracy of data from many such programs has not been adequately assessed. I evaluated a long-term, patrol-based wildlife monitoring system in Mole National Park, Ghana, through comparison with camera trapping and an assessment of sampling error. I found that patrol observations underrepresented the park’s mammal community, recording only two-thirds as many species as camera traps over a common sampling period (2006–2008). Agreement between methods was reasonable for larger, diurnal and social species (e.g., larger ungulates and primates), but camera traps were more effective at detecting smaller, solitary and nocturnal species (particularly carnivores). Data from patrols and cameras corresponded for some spatial patterns of management interest (e.g., community turnover, edge effect on abundance) but differed for others (e.g., richness, edge effect on diversity). Long-term patrol observations were influenced by uneven sampling effort and considerable variation in replicate counts. Despite potential benefits of locally-based monitoring, these results suggest that data from this and similar programs may be subject to biases that complicate interpretation of wildlife population and community dynamics. Careful attention to monitoring objectives, methodological design and robust analysis is required if locally-based approaches are to satisfy an aim of reliable biodiversity monitoring, and there is a need for greater international support in the creation and maintenance of local monitoring capacity.