Deep Learning Object Detection Methods for Ecological Camera Trap Data

1. Changes in insect biomass, abundance, and diversity are challenging to track at sufficient spatial, temporal, and taxonomic resolution. Camera traps can capture habitus images of ground-dwelling insects. However, currently sampling involves manually detecting and identifying specimens. Here, we test whether a convolutional neural network (CNN) can classify habitus images of ground beetles to species level, and estimate how correct classification relates to body size, number of species inside genera, and species identity.2. We created an image database of 65,841 museum specimens comprising 361 carabid beetle species from the British Isles and fine-tuned the parameters of a pretrained CNN from a training dataset. By summing up class confidence values within genus, tribe, and subfamily and setting a confidence threshold, we trade-off between classification accuracy, precision, and recall and taxonomic resolution.3. The CNN classified 51.9% of 19,164 test images correctly to species level and 74.9% to genus level. Average classification recall on species level was 50.7%.Applying a threshold of 0.5 increased the average classification recall to 74.6% at the expense of taxonomic resolution. Higher top value from the output layer and larger sized species were more often classified correctly, as were images of species in genera with few species. 4. Fine-tuning enabled us to classify images with a high mean recall for the whole test dataset to species or higher taxonomic levels, however, with high variability.This indicates that some species are more difficult to identify because of properties such as their body size or the number of related species.5. Together, species-level image classification of arthropods from museum collections and ecological monitoring can substantially increase the amount of occurrence data that can feasibly be collected. These tools thus provide new opportunities in understanding and predicting ecological responses to environmental change. Jens-Christian Svenninghttps://orcid.

Section: Discussionmentioning

confidence: 99%

Species‐level image classification with convolutional neural network enables insect identification from habitus images

Hansen

Svenning

Olsen

et al. 2019

“…Indeed, recent work on two classifiers has shown promise in quantifying animal species with accuracies of between 77% and 93% (Schneider, Taylor, & Kremer, 2018). Adaptations to enable these features would allow automatic estimation of ecologically important metrics such as population abundance and diversity.…”

Section: Discussionmentioning

confidence: 99%

Wildlife surveillance using deep learning methods

Chen

Little

Mihaylova

et al. 2019

Wildlife conservation and the management of human–wildlife conflicts require cost‐effective methods of monitoring wild animal behavior. Still and video camera surveillance can generate enormous quantities of data, which is laborious and expensive to screen for the species of interest. In the present study, we describe a state‐of‐the‐art, deep learning approach for automatically identifying and isolating species‐specific activity from still images and video data. We used a dataset consisting of 8,368 images of wild and domestic animals in farm buildings, and we developed an approach firstly to distinguish badgers from other species (binary classification) and secondly to distinguish each of six animal species (multiclassification). We focused on binary classification of badgers first because such a tool would be relevant to efforts to manage Mycobacterium bovis (the cause of bovine tuberculosis) transmission between badgers and cattle. We used two deep learning frameworks for automatic image recognition. They achieved high accuracies, in the order of 98.05% for binary classification and 90.32% for multiclassification. Based on the deep learning framework, a detection process was also developed for identifying animals of interest in video footage, which to our knowledge is the first application for this purpose. The algorithms developed here have wide applications in wildlife monitoring where large quantities of visual data require screening for certain species.

“…As previously discussed, various researchers are now applying image analysis, and in particular image recognition techniques, to classify images from camera traps. A typical objective is to see how well various recognition algorithms identify animal species (e.g., Norouzzadeha et al, ; Schneider et al, ; Tabak et al, ; Yousif et al, ), and even in recognizing individuals in particular species (e.g., Cheema & Anand, ; Crouse et al, ). Simpler image analysis methods can also identify other image aspects, for example, differentiate between color versus monochrome images, light versus dark images, and so on.…”

Section: Issue: Entering Datamentioning

confidence: 99%

“…The process can be repeated for other metadata of interest. A typical objective is to see how well various recognition algorithms identify animal species (e.g., Norouzzadeha et al, 2018;Schneider et al, 2018;Tabak et al, 2018;Yousif et al, 2019), and even in recognizing individuals in particular species (e.g., Cheema & Anand, 2017;Crouse et al, 2017 porates an image analyser that automatically classifies images against a user-configurable darkness threshold. Its classification is recorded in the "Image Quality" data field of every image as either "Dark" or "Ok." Timelapse also includes the ability to filter the displayed images by its data, which we will discuss shortly.…”

Section: Standard File Information Timelapse Template Schemas Alwaysmentioning

confidence: 99%

“…Recent research seeks to remedy this burden via automated image recognition, where promising wildlife species detection and identification rates have been reported (e.g., Norouzzadeha et al, 2018;Schneider, Taylor, & Kramer, 2018;Tabak et al, 2018;Yousif, Yuan, Kays, & He, 2019). Unfortunately, image recognition for camera traps is still in its formative stage.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Design patterns for wildlife‐related camera trap image analysis

Greenberg

Godin

Whittington

2019

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.