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

• URL: http://arxiv.org/abs/2609.03233v1
• Date: Thu, 03 Sep 2026 00:29:15 GMT
• Title: Counting Animals in Camera-Traps Image Sequences without Count Labels: Winning Solution to the iWildCam 2021 Challenge
• Abstract summary: We describe the winning solution to the iWildCam 2021 Challenge, which introduced a benchmark for counting animals at the sequence level.<n>Our approach, MaxBoxCount, combines a strong species classification pipeline with a simple yet effective counting based on MegaDetector detections.
• Score: 1.139527693693141
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Camera traps have become an essential tool for wildlife monitoring, motivating the development of computer vision methods for the automated extraction of information from these data. While most prior work has focused on species identification, many ecological applications also require estimating the number of unique individuals appearing across short image sequences. This task is particularly challenging because camera traps typically acquire bursts of images at approximately one frame per second, creating large temporal discontinuities that may make conventional multi-object tracking methods unreliable, and because manually collecting individual count annotations is prohibitively expensive. In this work, we describe the winning solution to the iWildCam 2021 Challenge, which introduced a benchmark for counting animals at the sequence level under realistic annotation constraints where count annotations are unavailable for training. Our approach, MaxBoxCount, combines a strong species classification pipeline with a simple yet effective counting heuristic based on MegaDetector detections to estimate the number of unique individuals without requiring count annotations. Code is available at https://github.com/alcunha/iwildcam2021ufam.

Related papers

• PuTR-CouT: Counting-by-Tracking in Camera-Trap Image Sequences [1.139527693693141]
  PuTR-CouT is a counting-by-tracking framework built on a transformer-based learned association mechanism for sequence-level animal counting in camera trap images.<n>Our framework delivers competitive counting results compared to the improved MaxBoxCount, with the added capability of multi-species predictions and track-level verification.
  arXiv  Detail & Related papers  (2026-09-04T11:57:22Z)
• CAMotion: A High-Quality Benchmark for Camouflaged Moving Object Detection in the Wild [83.45543969516149]
  In this paper, we construct CAMotion, a high-quality benchmark for camouflaged moving object detection in the wild.<n>The benchmark provides in-depth analyses on the camouflaged object's motion characteristics in different challenging scenarios.<n>We also conduct a comprehensive evaluation of existing SOTA models on CAMotion, and discuss the major challenges in VCOD task.
  arXiv  Detail & Related papers  (2026-04-09T14:23:46Z)
• Self-Supervised Animal Identification for Long Videos [0.8233028449337972]
  We introduce a highly efficient, self-supervised method that reframes animal identification as a global clustering task.<n>Our framework matches or surpasses supervised baselines trained on over 1,000 labeled frames.<n>This work enables practical, high-accuracy animal identification on consumer-grade hardware.
  arXiv  Detail & Related papers  (2026-01-14T17:53:59Z)
• Self-supervised Learning on Camera Trap Footage Yields a Strong Universal Face Embedder [48.03572115000886]
  This study introduces a fully self-supervised approach to learning robust chimpanzee face embeddings from unlabeled camera-trap footage.<n>We train Vision Transformers on automatically mined face crops, eliminating the need for identity labels.<n>This work underscores the potential of self-supervised learning in biodiversity monitoring and paves the way for scalable, non-invasive population studies.
  arXiv  Detail & Related papers  (2025-07-14T17:59:59Z)
• One Diffusion to Generate Them All [54.82732533013014]
  OneDiffusion is a versatile, large-scale diffusion model that supports bidirectional image synthesis and understanding.<n>It enables conditional generation from inputs such as text, depth, pose, layout, and semantic maps.<n>OneDiffusion allows for multi-view generation, camera pose estimation, and instant personalization using sequential image inputs.
  arXiv  Detail & Related papers  (2024-11-25T12:11:05Z)
• Learning Camouflaged Object Detection from Noisy Pseudo Label [60.9005578956798]
  This paper introduces the first weakly semi-supervised Camouflaged Object Detection (COD) method. It aims for budget-efficient and high-precision camouflaged object segmentation with an extremely limited number of fully labeled images. We propose a noise correction loss that facilitates the model's learning of correct pixels in the early learning stage. When using only 20% of fully labeled data, our method shows superior performance over the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-18T04:53:51Z)
• Multimodal Foundation Models for Zero-shot Animal Species Recognition in Camera Trap Images [57.96659470133514]
  Motion-activated camera traps constitute an efficient tool for tracking and monitoring wildlife populations across the globe. Supervised learning techniques have been successfully deployed to analyze such imagery, however training such techniques requires annotations from experts. Reducing the reliance on costly labelled data has immense potential in developing large-scale wildlife tracking solutions with markedly less human labor.
  arXiv  Detail & Related papers  (2023-11-02T08:32:00Z)
• CamDiff: Camouflage Image Augmentation via Diffusion Model [83.35960536063857]
  CamDiff is a novel approach to synthesize salient objects in camouflaged scenes. We leverage the latent diffusion model to synthesize salient objects in camouflaged scenes. Our approach enables flexible editing and efficient large-scale dataset generation at a low cost.
  arXiv  Detail & Related papers  (2023-04-11T19:37:47Z)
• Efficiently Collecting Training Dataset for 2D Object Detection by Online Visual Feedback [5.015678820698308]
  Training deep-learning-based vision systems require the manual annotation of a significant number of images. We propose a human-in-the-loop dataset collection method that uses a web application. To counterbalance the workload and performance by encouraging the collection of multi-view object image datasets in an enjoyable manner, we propose three types of online visual feedback features.
  arXiv  Detail & Related papers  (2023-04-11T00:17:28Z)
• The iWildCam 2021 Competition Dataset [5.612688040565423]
  Ecologists use camera traps to monitor animal populations all over the world. To estimate the abundance of a species, ecologists need to know not just which species were seen, but how many individuals of each species were seen. We have prepared a challenge where the training data and test data are from different cameras spread across the globe.
  arXiv  Detail & Related papers  (2021-05-07T20:27:22Z)
• Automatic Detection and Recognition of Individuals in Patterned Species [4.163860911052052]
  We develop a framework for automatic detection and recognition of individuals in different patterned species. We use the recently proposed Faster-RCNN object detection framework to efficiently detect animals in images. We evaluate our recognition system on zebra and jaguar images to show generalization to other patterned species.
  arXiv  Detail & Related papers  (2020-05-06T15:29:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.