arXiv Computer Vision

PuTR-CouT: Counting-by-Tracking in Camera-Trap Image Sequences

PuTR-CouT is a transformer‑based counting‑by‑tracking framework designed for camera‑trap image sequences. It generates synthetic training data using structural priors to create pseudo‑tracking labels, enabling the tracker to associate detections across frames and estimate per‑species counts. The method improves upon the MaxBoxCount baseline on the iWildCam 2021 benchmark, offering competitive counting results along with multi‑species predictions and track‑level verification.

arXiv Computer Vision
Sep 4

Counting Animals in Camera-Traps Image Sequences without Count Labels: Winning Solution to the iWildCam 2021 Challenge

The paper presents MaxBoxCount, the winning solution to the iWildCam 2021 Challenge, which tackles counting animals in camera‑trap image sequences without using count labels. It combines a robust species classification pipeline with a counting heuristic based on MegaDetector detections to estimate the number of unique individuals across short image bursts. The method addresses challenges posed by temporal discontinuities and the high cost of manual count annotations.

By Fagner Cunha, Juan G. Colonna, Eulanda M. dos Santos
arXiv Computer Vision
3d ago

GorillaWatch: An Automated System for In-the-Wild Gorilla Re-Identification and Population Monitoring

arXiv:2512.07776v2 Announce Type: replace Abstract: Monitoring critically endangered western lowland gorillas is currently hampered by the immense manual effort required to re-identify individuals fr...

By Maximilian Schall, Felix Leonard Kn\"ofel, Noah Elias K\"onig, Jan Jonas Kubeler, Maximilian von Klinski, Joan Wilhelm Linnemann, Xiaoshi Liu, Iven Jelle Schlegelmilch, Ole Woyciniuk, Alexandra Schild, Dante Wasmuht, Magdalena Bermejo Espinet, German Illera Basas, Gerard de Melo
Hugging Face Trending Papers
Aug 5

Promptable Animal Pose Tracking Across Species

Animal pose estimation and tracking is important for wildlife monitoring and conservation research, and with limited expert time for labelling automated approaches are imperative. While human pose estimation and tracking has seen rapid progress thanks to large annotated datasets, animal pose remain challenging, due to large morphological and behavioural differences between species and limited annotated data.

arXiv AI
Jun 10

Democratising Camera Trap AI: An Open-Source Model for Detecting UK Mammals

arXiv:2606. 10940v1 Announce Type: cross Abstract: Camera traps have become a cornerstone of biodiversity monitoring, but the artificial intelligence that turns vast quantities of images into usable ecological data is often locked behind commercial platforms or trained on fauna that does not match that of the British Isles.

By Paul Fergus, Philip Stephens, Russell A. Hill, Lee Oliver, Katie Appleby, Sarah Beatham, Naomi Davies Walsh, Stuart Nixon, Naomi Matthews, Chris Sutherland, Kelly Hitchcock
arXiv Computer Vision
Aug 24

WildFin: An In-the-Wild Dataset for Fish Behavioral Recognition

arXiv:2608.21281v1 Announce Type: new Abstract: Recent advances in field technology have led to a massive influx of in-the-wild video data for ecological science. The primary bottleneck in leveraging...

By Abigail G. Grassick, Jerome Tze-Hou Hsu, Ethan Lin, Ziang Liu, Max Whitton, Madelyn Hair, Liam Gutierrez, Haozheng Yu, Kristin Branson, Vivek Jayaraman, Michael A. Gil, Andrew M. Hein, Jennifer J. Sun
Hugging Face Trending Papers
Jun 9

Democratising Camera Trap AI: An Open-Source Model for Detecting UK Mammals

Camera traps have become a cornerstone of biodiversity monitoring, but the artificial intelligence that turns vast quantities of images into usable ecological data is often locked behind commercial platforms or trained on fauna that does not match that of the British Isles. In an attempt to remove barriers and increase uptake, we release an open-source object detection model for 31 classes, 28 common UK mammal and bird species, plus utility classes for humans, calibration poles, and vehicles, drawn from a curated dataset of 48,165 labelled instances assembled from multiple sites over a decade of operational deployment through Conservation AI and its successor, Trap Tracker.

arXiv Computer Vision
Sep 3

SelfMOTR: Revisiting MOTR with Self-Generating Detection Priors

SelfMOTR proposes a detector‑free approach to multi‑object tracking that decouples proposal discovery from association by generating internal detection priors. The method builds on end‑to‑end transformer trackers, showing that joint detection‑association decoding retains hidden detection capacity and can be leveraged without external detectors. Experiments demonstrate competitive results, achieving 69.2 HOTA on DanceTrack and 71.1 HOTA on Bird Flock Tracking.

By Fabian G\"ulhan, Emil Mededovic, Yuli Wu, Johannes Stegmaier
arXiv Computer Vision
Sep 7

Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods

The paper introduces MovingDroneCrowd++, a large-scale video dataset for dense crowd counting and tracking from moving drones, featuring varied flight altitudes, camera angles, and lighting. It presents two new methods: GD3A for Video Individual Counting and GIA-Track for Multi-Object Tracking, both leveraging group-wise density assignment and identity association to handle aerial challenges. Experiments demonstrate significant improvements, reducing counting error by 47.4% and boosting tracking accuracy by 64.6%.

By Yaowu Fan, Jia Wan, Tao Han, Andy J. Ma, Wanli Ouyang, Antoni B. Chan
arXiv Computer Vision
Sep 4

BMCTrack-d: Pig re-identification and tracking via back marks in challenging camera settings

BMCTrack-d is a novel tracking-by-detection method that uses unique back marks on pigs to achieve robust re-identification and tracking in challenging side-view camera settings. The approach employs a neural network-based back mark classifier followed by temporal consistency checks and deduplication to improve identity reliability over time. On a demanding test set, BMCTrack-d outperforms strong baselines, achieving higher-order tracking accuracy gains of 9.11% and 1.03%.

By David Brunner, Maciej Oczak, Marie Bordes, Jean-Loup Rault, Stephan M. Winkler, Viktoria Dorfer