Saved in:
Bibliographic Details
Main Authors: Russello, Helena, van der Tol, Rik, van Henten, Eldert J., Kootstra, Gert
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.10643
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913991569178624
author Russello, Helena
van der Tol, Rik
van Henten, Eldert J.
Kootstra, Gert
author_facet Russello, Helena
van der Tol, Rik
van Henten, Eldert J.
Kootstra, Gert
contents This study presents a lameness detection approach that combines pose estimation and Bidirectional Long-Short-Term Memory (BLSTM) neural networks. Combining pose-estimation and BLSTMs classifier offers the following advantages: markerless pose-estimation, elimination of manual feature engineering by learning temporal motion features from the keypoint trajectories, and working with short sequences and small training datasets. Motion sequences of nine keypoints (located on the cows' hooves, head and back) were extracted from videos of walking cows with the T-LEAP pose estimation model. The trajectories of the keypoints were then used as an input to a BLSTM classifier that was trained to perform binary lameness classification. Our method significantly outperformed an established method that relied on manually-designed locomotion features: our best architecture achieved a classification accuracy of 85%, against 80% accuracy for the feature-based approach. Furthermore, we showed that our BLSTM classifier could detect lameness with as little as one second of video data.
format Preprint
id arxiv_https___arxiv_org_abs_2508_10643
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Lameness detection in dairy cows using pose estimation and bidirectional LSTMs
Russello, Helena
van der Tol, Rik
van Henten, Eldert J.
Kootstra, Gert
Computer Vision and Pattern Recognition
This study presents a lameness detection approach that combines pose estimation and Bidirectional Long-Short-Term Memory (BLSTM) neural networks. Combining pose-estimation and BLSTMs classifier offers the following advantages: markerless pose-estimation, elimination of manual feature engineering by learning temporal motion features from the keypoint trajectories, and working with short sequences and small training datasets. Motion sequences of nine keypoints (located on the cows' hooves, head and back) were extracted from videos of walking cows with the T-LEAP pose estimation model. The trajectories of the keypoints were then used as an input to a BLSTM classifier that was trained to perform binary lameness classification. Our method significantly outperformed an established method that relied on manually-designed locomotion features: our best architecture achieved a classification accuracy of 85%, against 80% accuracy for the feature-based approach. Furthermore, we showed that our BLSTM classifier could detect lameness with as little as one second of video data.
title Lameness detection in dairy cows using pose estimation and bidirectional LSTMs
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.10643