Fast Visual Object Tracking using Ellipse Fitting for Rotated Bounding Boxes

The Visual Object Tracking challenge VOT2019 is the seventh annual tracker benchmarking activity organized by the VOT initiative. Results of 81 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The evaluation included the standard VOT and other popular methodologies for short-term tracking analysis as well as the standard VOT methodology for long-term tracking analysis. The VOT2019 challenge was composed of five challenges focusing on different tracking domains: (i) VOT-ST2019 challenge focused on short-term tracking in RGB, (ii) VOT-RT2019 challenge focused on "real-time" shortterm tracking in RGB, (iii) VOT-LT2019 focused on longterm tracking namely coping with target disappearance and reappearance. Two new challenges have been introduced: (iv) VOT-RGBT2019 challenge focused on short-term tracking in RGB and thermal imagery and (v) VOT-RGBD2019 challenge focused on long-term tracking in RGB and depth imagery. The VOT-ST2019, VOT-RT2019 and VOT-LT2019 datasets were refreshed while new datasets were introduced for VOT-RGBT2019 and VOT-RGBD2019. The VOT toolkit has been updated to support both standard shortterm, long-term tracking and tracking with multi-channel imagery. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website 1 .

show abstract

“…Then, rotate the mask and apply an up-right bounding rectangle to the rotated mask. We also developed a new version called SiamMask E [11].…”

Section: A45 Fitting Siamese Mask With Ellipses For Objectmentioning

confidence: 99%

The Seventh Visual Object Tracking VOT2019 Challenge Results

Kristan

Berg

Zheng

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

Self Cite

363

359

View full text Add to dashboard Cite

show abstract

“…By capturing the motion information of the entire human subject, global representations are richer and express better and more concise motion information. Although they are susceptible to noise, the current advances in human detector [39][40][41][42], human tracker [43][44][45][46], and multi-person tracker [47][48][49][50] algorithms, make it easier to achieve high accuracy even with occlusions, different viewpoints, or noise, as shown in Figure 4. Despite the object detectors and trackers accuracy, they capture the information in a certain rectangle region, which may introduce some noise and irrelevant information, not only from the human appearance but also the cluttered background.…”

Section: Global Representationsmentioning

confidence: 99%

Human Behavior Analysis: A Survey on Action Recognition

Degardin

Proença

2021

Applied Sciences

View full text Add to dashboard Cite

The visual recognition and understanding of human actions remain an active research domain of computer vision, being the scope of various research works over the last two decades. The problem is challenging due to its many interpersonal variations in appearance and motion dynamics between humans, without forgetting the environmental heterogeneity between different video images. This complexity splits the problem into two major categories: action classification, recognising the action being performed in the scene, and spatiotemporal action localisation, concerning recognising multiple localised human actions present in the scene. Previous surveys mainly focus on the evolution of this field, from handcrafted features to deep learning architectures. However, this survey presents an overview of both categories and respective evolution within each one, the guidelines that should be followed and the current benchmarks employed for performance comparison between the state-of-the-art methods.

show abstract

“…Recently, an oriented bounding box (OBB) has been adopted in localizing objects in photos [6]- [10]. There are two ways to represent an OBB.…”

Section: Introductionmentioning

confidence: 99%

“…This scheme, however, requires more computing time due to the pixel-wise computation of IOUs. Chen and Tsotsos [10] used bounding ellipses for visual object tracking but had a limitation whereby a segmentation/mask of an object should be given. Furthermore, their method also requires the computation of IOUs for training, which is different from the proposed approach that is free from computing IOUs.…”

Section: Introductionmentioning

confidence: 99%

Non-Anchor-Based Vehicle Detection for Traffic Surveillance Using Bounding Ellipses

Shin

Kim

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Cameras for traffic surveillance are usually pole-mounted and produce images that reflect a birds-eye view. Vehicles in such images, in general, assume an ellipse form. A bounding box for the vehicles usually includes a large empty space when the vehicle orientation is not parallel to the edges of the box. To circumvent this problem, the present study applied bounding ellipses to a non-anchor-based, single-shot detection model (CenterNet). Since this model does not depend on anchor boxes, non-max suppression (NMS) that requires computing the intersection over union (IOU) between predicted bounding boxes is unnecessary for inference. The SpotNet that extends the CenterNet model by adding a segmentation head was also tested with bounding ellipses. Two other anchor-based, single-shot detection models (YOLO4 and SSD) were chosen as references for comparison. The model performance was compared based on a local dataset that was doubly annotated with bounding boxes and ellipses. As a result, the performance of the two models with bounding ellipses exceeded that of the reference models with bounding boxes. When the backbone of the ellipse models was pretrained on an open dataset (UA-DETRAC), the performance was further enhanced. Several data augmentation schemes also improved the performance of the proposed models. As a result, the best mAP score of a CenterNet exceeds 0.95 when augmenting heatmaps with bounding ellipses.

show abstract

Fast Visual Object Tracking using Ellipse Fitting for Rotated Bounding Boxes

Cited by 19 publications

References 42 publications

The Seventh Visual Object Tracking VOT2019 Challenge Results

The Seventh Visual Object Tracking VOT2019 Challenge Results

Human Behavior Analysis: A Survey on Action Recognition

Non-Anchor-Based Vehicle Detection for Traffic Surveillance Using Bounding Ellipses

Contact Info

Product

Resources

About