Skip to content
Open access

PACTraD: Multi-Task Benchmark and Domain-Specific Attention Mechanism for Wildlife Classification, Detection, and Segmentation in Protected Area Camera Trap Data

Oct 2026 · Big Data and Cognitive Computing · Vol 10, pp. 363 · 0 citations · 43 references

TL;DR

PACTraD is introduced, a benchmark of 116,973 annotated camera trap images collected in a protected area of the Baikal region across eight classes with a pronounced long-tailed distribution, and a domain-specific attention mechanism augmenting self-attention with eleven learnable priors.

Abstract

Camera traps are a key tool for non-invasive wildlife monitoring, yet models trained on existing benchmarks often generalize poorly to new regions due to domain shift, class imbalance, and natural variability in illumination, season, and background. We introduce PACTraD, a benchmark of 116,973 annotated camera trap images collected in a protected area of the Baikal region across eight classes (deer, no_animals, bear, boar, hare, badger, lynx, wolf), with a pronounced long-tailed distribution (deer: 73.1%; lynx and wolf: 0.3% and 0.2%) and substantial seasonal and lighting variability, including infrared night imagery. The benchmark supports three tasks under a unified, reproducible protocol: classification, object detection, and semantic segmentation. We further propose a domain-specific attention mechanism augmenting self-attention with eleven learnable priors capturing contour, foreground/background separation, bilateral symmetry, discriminative part regions, texture frequency, confidence weighting, motion consistency, gradient enhancement, scale, color invariance, and shape compactness. Evaluated on six backbones for classification and detection and five for segmentation, against no-attention baselines and three generic attention modules (SE, SA, CBAM), it consistently performs best, raising weighted F1 for classification from 0.943 to 0.964 (DINOv3), AP50 for detection from 0.876 to 0.903 (InternImage-H), and mIoU for segmentation from 0.805 to 0.834 (SegMAN), with component-level ablations revealing task-specific contributions of each prior. However, performance on rare species remains limited (macro F1: 0.829 for classification), indicating that further research is needed to address long-tail recognition in camera trap data.

Read PDF

Similar papers

Automated Species Identification in Camera Trap Images for Wildlife Conservation

A novel end-to-end framework integrating a self-attention mechanism to address limitations in effectively detecting small animals in low-contrast trap images and small animals while also demonstrating zero-shot detection capability leveraging the MLLM.

N. Amin, Nafisa Tabassum Oyshi, Tahmid Abrar Zidan et al. · 0 citations
Conference Open access Oct 2026

Towards Benchmarking Western Bluebird Detection in the Wild

Bird monitoring in natural environments is challenging due to the small size of some species of birds relative to the scene, background clutter, variability in illumination, and the observers'viewpoint. Progress is further limited by the scarcity of large-scale, realistic datasets, which are essential for understanding...

Estela Monserrat Arriaga Santana, Julian Rosas Scull, Ibeth P. Alarcón et al. · 0 citations
Open access Oct 2026

Hjort-YOLO: a lightweight and explainable computer vision framework for wildlife detection

Introduction Automated animal detection is an important component of ecological monitoring and may in the future be used also for wildlife vehicle collision mitigation by constructing efficient alert systems. However, the often complex environmental background in habitats along roads and different sizes due to the dist...

Md Abdul Momin, Mehak Khan, Reza Arghandeh et al. · 0 citations
Review Oct 2026

A unified three-branch deep learning framework for automated detection and counting of wildlife in aerial imagery

Automating aerial wildlife surveys requires reliable animal detection, consistent delineation of observation strips, and correction for repeated coverage between successive images. We present a unified three-branch deep learning framework that integrates these tasks through WildSeg, WildMatch and WildDet. WildSeg combi...

Ze-Yu Xu, Tie-Jun Wang, Andrew K. Skidmore et al. · 0 citations
Review Open access Oct 2026

LSARE-Net: Target-Guided Augmentation and Lightweight Edge Detection for Real-Time Behavior Monitoring of Captive Juvenile Sika Deer

Simple Summary While continuous monitoring can reveal changes in deer behavior, manually reviewing surveillance footage is both time-consuming and labor-intensive. To address this, we developed a camera-based system to detect five behavioral categories in group-housed juvenile sika deer: resting, standing, feeding, soc...

Xi-Peng Li, He Pan, Adnan Mahmood et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.