ultralytics/yolov3: v9.5.0 - YOLOv5 v5.0 release compatibility update for YOLOv3

Jocher, Glenn; Kwon, Yonghye; guigarfr,; Perry,; Veitch-Michaelis, Josh; Ttayu,; Suess, Dieter; Baltacı, Fatih; Bianconi, Gabriel; IlyaOvodov,; Marć, Paweł; Brasier, Allan R.; Kendall, Dustin; Falak,; Reveriano, Francisco; Fulin,; GoogleWiki,; Nataprawira, Jason; Hu, Jeremy; LinCoce,; LukeAI,; NanoCode,; NirZarrabi,; Oulbacha, Reda; Skalski, Piotr; SergioSanchezMontesUAM,; Song, Shiwei; Havlik, Thomas; Shead, Timothy M.

doi:10.5281/zenodo.4681234

Cited by 7 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ResNet101 [ 3 ] was used in other detectors as the backbone network. These detectors were trained for 2x epochs, using the data augment strategies that the default YOLO detectors used, such as mixup [ 44 ], mosaic [ 45 ], and photometric distortions. Other settings were left as the default public implements [ 22 , 23 , 45 , 46 ].…”

Section: Experiments and Resultsmentioning

confidence: 99%

LAG: Layered Objects to Generate Better Anchors for Object Detection in Aerial Images

Wan

Tan

et al. 2022

Sensors

View full text Add to dashboard Cite

You Only Look Once (YOLO) series detectors are suitable for aerial image object detection because of their excellent real-time ability and performance. Their high performance depends heavily on the anchor generated by clustering the training set. However, the effectiveness of the general Anchor Generation algorithm is limited by the unique data distribution of the aerial image dataset. The divergence in the distribution of the number of objects with different sizes can cause the anchors to overfit some objects or be assigned to suboptimal layers because anchors of each layer are generated uniformly and affected by the overall data distribution. In this paper, we are inspired by experiments under different anchors settings and proposed the Layered Anchor Generation (LAG) algorithm. In the LAG, objects are layered by their diagonals, and then anchors of each layer are generated by analyzing the diagonals and aspect ratio of objects of the corresponding layer. In this way, anchors of each layer can better match the detection range of each layer. Experiment results showed that our algorithm is of good generality that significantly uprises the performance of You Only Look Once version 3 (YOLOv3), You Only Look Once version 5 (YOLOv5), You Only Learn One Representation (YOLOR), and Cascade Regions with CNN features (Cascade R-CNN) on the Vision Meets Drone (VisDrone) dataset and the object DetectIon in Optical Remote sensing images (DIOR) dataset, and these improvements are cost-free.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

LAG: Layered Objects to Generate Better Anchors for Object Detection in Aerial Images

Wan

Tan

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…For evaluation in combination with obstacle avoidance in close to real-life expected situations, we equipped the robot Qolo [22] with 2 Lidars (Velodyne VLP-16), and an RGBD sensor (Intel Realsense). Obstacle's tracking was performed through real-time people detection implemented through a pipeline of sensing fusion of Lidar-based detection by DR-SPAAM [28] and RGBD detection through YOLO [29]. The full controller repository can be found here: Qolo-ROS [30].…”

Section: Experimental Evaluationmentioning

confidence: 99%

Unfreezing Social Navigation: Dynamical Systems based Compliance for Contact Control in Robot Navigation

Paez-Granados¹,

Gupta²,

Billard³

2022

Preprint

View full text Add to dashboard Cite

“…A key component for crowd navigation is the localization and tracking of the environment and crowd (Ξ). We have set people tracking through a real-time pipeline of sensing fusion of Lidar-based detection by DR-SPAAM [21] and RGBD detection by YOLO [22]. Whereas robot state (ξ) was estimated on optical flow principle from a stereo camera (Intel T265) fused with IMU and odometry.…”

Section: Introductionmentioning

confidence: 99%

Pedestrian-Robot Interactions on Autonomous Crowd Navigation: Reactive Control Methods and Evaluation Metrics

Paez-Granados

Gonon

et al. 2022

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Autonomous navigation in highly populated areas remains a challenging task for robots because of the difficulty in guaranteeing safe interactions with pedestrians in unstructured situations. In this work, we present a crowd navigation control framework that delivers continuous obstacle avoidance and post-contact control evaluated on an autonomous personal mobility vehicle. We propose evaluation metrics for accounting efficiency, controller response and crowd interactions in natural crowds. We report the results of over 110 trials in different crowd types: sparse, flows, and mixed traffic, with low-(< 0.15 ppsm), mid-(< 0.65 ppsm), and high-(< 1 ppsm) pedestrian densities. We present comparative results between two low-level obstacle avoidance methods and a baseline of shared control. Results show a 10% drop in relative time to goal on the highest density tests, and no other efficiency metric decrease. Moreover, autonomous navigation showed to be comparable to shared-control navigation with a lower relative jerk and significantly higher fluency in commands indicating high compatibility with the crowd. We conclude that the reactive controller fulfils a necessary task of fast and continuous adaptation to crowd navigation, and it should be coupled with high-level planners for environmental and situational awareness.

show abstract

ultralytics/yolov3: v9.5.0 - YOLOv5 v5.0 release compatibility update for YOLOv3

Cited by 7 publications

References 0 publications

LAG: Layered Objects to Generate Better Anchors for Object Detection in Aerial Images

LAG: Layered Objects to Generate Better Anchors for Object Detection in Aerial Images

Unfreezing Social Navigation: Dynamical Systems based Compliance for Contact Control in Robot Navigation

Pedestrian-Robot Interactions on Autonomous Crowd Navigation: Reactive Control Methods and Evaluation Metrics

Contact Info

Product

Resources

About