YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss

Maji, Debapriya; Nagori, Soyeb; Mathew, Manu; Poddar, Deepak

doi:10.48550/arxiv.2204.06806

Cited by 11 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While there exist several models that jointly predict keypoints and descriptors, there are to our knowledge none that also detect objects in the same network. Maji et al's work [15] comes closest to ours. They use YOLOv5 to jointly predict keypoints for human pose estimation as well as bounding boxes in a single forward pass.…”

Section: Related Worksupporting

confidence: 58%

YOLOPoint: Joint Keypoint and Object Detection

Backhaus,

Luettel,

Wuensche

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Intelligent vehicles of the future must be capable of understanding and navigating safely through their surroundings. Camerabased vehicle systems can use keypoints as well as objects as low-and high-level landmarks for GNSS-independent SLAM and visual odometry. To this end we propose YOLOPoint, a convolutional neural network model that simultaneously detects keypoints and objects in an image by combining YOLOv5 and SuperPoint to create a single forward-pass network that is both real-time capable and accurate. By using a shared backbone and a light-weight network structure, YOLOPoint is able to perform competitively on both the HPatches and KITTI benchmarks.

show abstract

Section: Related Worksupporting

confidence: 58%

YOLOPoint: Joint Keypoint and Object Detection

Backhaus,

Luettel,

Wuensche

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…YOLO-Pose [32] proposes an extension of anchor-based architectures to predict keypoints. Compared to YOLO-HRNet, the model size of YOLO-Pose [32] is reduced and predictions are made within one stage. A significant improvement in inference speed but worse prediction accuracy are expected.…”

Section: Methodsmentioning

confidence: 99%

Real-Time Joint-Stem Prediction for Agricultural Robots in Grasslands Using Multi-Task Learning

Li,

Güldenring,

Nalpantidis

2023

Agronomy

View full text Add to dashboard Cite

Autonomous weeding robots need to accurately detect the joint stem of grassland weeds in order to control those weeds in an effective and energy-efficient manner. In this work, keypoints on joint stems and bounding boxes around weeds in grasslands are detected jointly using multi-task learning. We compare a two-stage, heatmap-based architecture to a single-stage, regression-based architecture—both based on the popular YOLOv5 object detector. Our results show that introducing joint-stem detection as a second task boosts the individual weed detection performance in both architectures. Furthermore, the single-stage architecture clearly outperforms its competitors with an OKS of 56.3 in joint-stem detection while also achieving real-time performance of 12.2 FPS on Nvidia Jetson NX, suitable for agricultural robots. Finally, we make the newly created joint-stem ground-truth annotations publicly available for the relevant research community.

show abstract

“…On the loss computation front, YOLOv8 employs the positive sample distribution technique of the TaskAlignedAssigner and integrates the Distribution Focal Loss for added efficacy. Venturing into pose estimation, Yolopose [19] offers a groundbreaking solution. Built upon the YOLO foundation, it negates the need for heatmaps.…”

Section: Human Body Posture Estimationmentioning

confidence: 99%

Single-Stage Pose Estimation and Joint Angle Extraction Method for Moving Human Body

Wang,

Zhang,

et al. 2023

Electronics

View full text Add to dashboard Cite

Detecting posture changes of athletes in sports is an important task in teaching and training competitions, but its detection remains challenging due to the diversity and complexity of sports postures. This paper introduces a single-stage pose estimation algorithm named yolov8-sp. This algorithm enhances the original yolov8 architecture by incorporating the concept of multi-dimensional feature fusion and the attention mechanism for automatically capturing feature importance. Furthermore, in this paper, angle extraction is conducted for three crucial motion joints in the motion scene, with polynomial corrections applied across successive frames. In comparison with the baseline yolov8, the improved model significantly outperforms it in AP50 (average precision) aspects. Specifically, the model’s performance improves from 84.5 AP to 87.1 AP, and the performance of AP50–95, APM, and APL aspects also shows varying degrees of improvement; the joint angle detection accuracy under different sports scenarios is tested, and the overall accuracy is improved from 73.2% to 89.0%, which proves the feasibility of the method for posture estimation of the human body in sports and provides a reliable tool for the analysis of athletes’ joint angles.

show abstract

YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss

Cited by 11 publications

References 0 publications

YOLOPoint: Joint Keypoint and Object Detection

YOLOPoint: Joint Keypoint and Object Detection

Real-Time Joint-Stem Prediction for Agricultural Robots in Grasslands Using Multi-Task Learning

Single-Stage Pose Estimation and Joint Angle Extraction Method for Moving Human Body

Contact Info

Product

Resources

About