Automated face detection for occurrence and occupancy estimation in chimpanzees

Crunchant, Anne Sophie; Egerer, Monika; Loos, Alexander; Burghardt, Tilo; Zuberbühler, Klaus; Corogenes, Katherine; Leinert, Vera; Kulik, Lars; Kühl, Hjalmar S.

doi:10.1002/ajp.22627

Cited by 21 publications

(9 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent progress in the emerging field of animal biometrics [36], in particular in ape facial recognition [47,12,46,16] promises to overcome some of these obstacles and make broad-scale, real-world applications a realistic prospect.…”

Section: Monitoring In Ecology Todaymentioning

confidence: 99%

“…In addition, once images are interpreted, statistical tools [25] applied to visual sighting data can be used to estimate abundance in a study area. However, the manual effort required to conduct such studies currently limits their application [12]. The processing of the number of images or footage collected with even only a few devices quickly exceeds any capacity available.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards Automated Visual Monitoring of Individual Gorillas in the Wild

Brust

Burghardt

Groenenberg

et al. 2017

2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

Self Cite

View full text Add to dashboard Cite

In this paper we report on the context and evaluation of a system for an automatic interpretation of sightings of individual western lowland gorillas (Gorilla gorilla gorilla) as captured in facial fieldVisual data acquisition in the field often captures sufficient information to establish encounters with individual gorillas. However, relevant information is locked within the pixel patterns measured, usually requiring expert knowledge and time-consuming efforts for identification. Computer vision can help to extract gorilla identities by performing automated species detection, followed by individual facial identification. We show that standard deep learning models combined with a traditional SVM classifier can be used for this task. To assist encounter processing, predictions can be presented graphically with known population information as shown.

show abstract

Section: Monitoring In Ecology Todaymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Towards Automated Visual Monitoring of Individual Gorillas in the Wild

Brust

Burghardt

Groenenberg

et al. 2017

2017 IEEE International Conference on Computer Vision Workshops (ICCVW)

Self Cite

View full text Add to dashboard Cite

show abstract

“…A manual validation to clean false positives is, however, necessary (e.g. Campos‐Cerqueira & Aide, ; Crunchant et al, ; Enari et al, ; Kalan et al, ) to control for false positives. With species with high‐call variabilities, like chimpanzees, developing an algorithm is more challenging but as technology improves rapidly, we can expect the development of a detection algorithm in the near future.…”

Section: Discussionmentioning

confidence: 99%

Listening and watching: Do camera traps or acoustic sensors more efficiently detect wild chimpanzees in an open habitat?

et al. 2020

View full text Add to dashboard Cite

With one million animal species at risk of extinction, there is an urgent need to regularly monitor threatened species. However, in practice this is challenging, especially with wide‐ranging, elusive and cryptic species or those that occur at low density. Here we compare two non‐invasive methods, passive acoustic monitoring (n = 12) and camera trapping (n = 53), to detect chimpanzees Pan troglodytes in a savanna‐woodland mosaic habitat at the Issa Valley, Tanzania. With occupancy modelling we evaluate the efficacy of each method, using the estimated number of sampling days needed to establish chimpanzee absence with 95% probability, as our measure of efficacy. Passive acoustic monitoring was more efficient than camera trapping in detecting wild chimpanzees. Detectability varied over seasons, likely due to social and ecological factors that influence party size and vocalization rate. The acoustic method can infer chimpanzee absence with less than 10 days of recordings in the field during the late dry season, the period of highest detectability, which was five times faster than the visual method. Synthesis and applications. Despite some technical limitations, we demonstrate that passive acoustic monitoring is a powerful tool for species monitoring. Its applicability in evaluating presence/absence, especially but not exclusively for loud call species, such as cetaceans, elephants, gibbons or chimpanzees provides a more efficient way of monitoring populations and inform conservation plans to mediate species‐loss.

show abstract

“…We note that currently ecological camera trap studies are widely conducted by manual inspection, although great ape face detection [2,21] has been used for ecological surveys before [7] and DrivenData [8] hosted a recent challenge to classify jungle camera trap clips by species, without detecting animals and their location in frames explicitly.…”

Section: Discussionmentioning

confidence: 99%

Great Ape Detection in Challenging Jungle Camera Trap Footage via Attention-Based Spatial and Temporal Feature Blending

Yang

Mirmehdi

Burghardt

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

Self Cite

View full text Add to dashboard Cite

We propose the first multi-frame video object detection framework trained to detect great apes. It is applicable to challenging camera trap footage in complex jungle environments and extends a traditional feature pyramid architecture by adding self-attention driven feature blending in both the spatial as well as the temporal domain. We demonstrate that this extension can detect distinctive species appearance and motion signatures despite significant partial occlusion. We evaluate the framework using 500 camera trap videos of great apes from the Pan African Programme containing 180K frames, which we manually annotated with accurate per-frame animal bounding boxes. These clips contain significant partial occlusions, challenging lighting, dynamic backgrounds, and natural camouflage effects. We show that our approach performs highly robustly and significantly outperforms frame-based detectors. We also perform detailed ablation studies and a validation on the full ILSVRC 2015 VID data corpus to demonstrate wider applicability at adequate performance levels. We conclude that the framework is ready to assist human camera trap inspection efforts. We publish key parts of the code as well as network weights and ground truth annotations with this paper.

show abstract

Automated face detection for occurrence and occupancy estimation in chimpanzees

Abstract: Using semi-automated ape face detection technology for processing camera trap footage requires only 2-4% of the time compared to manual analysis and allows to estimate site use by chimpanzees relatively reliably.

Cited by 21 publications

References 59 publications

Towards Automated Visual Monitoring of Individual Gorillas in the Wild

Towards Automated Visual Monitoring of Individual Gorillas in the Wild

Listening and watching: Do camera traps or acoustic sensors more efficiently detect wild chimpanzees in an open habitat?

Great Ape Detection in Challenging Jungle Camera Trap Footage via Attention-Based Spatial and Temporal Feature Blending

Contact Info

Product

Resources

About