RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images

Duan, Zhihao; Tezcan, M. Ozan; Nakamura, Hayato; Ishwar, Prakash; Konrad, Janusz

doi:10.1109/cvprw50498.2020.00326

Cited by 65 publications

(36 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is done by first detecting and tracking the persons in 360 • video frames who are close to the centre, and then extracting spatio-temporal features from them. For person detection, we use the Rotation-Aware People Detection method RAPiD [22] trained on top-view 360 • images. It outputs the bounding box co-ordinates of all persons present in the 360 • video frame (co-ordinates of the centroid of the bounding box, its width, height, angle of rotation and confidence of detection).…”

Section: Proposed Methodsmentioning

confidence: 99%

A Hybrid two-stream approach for Multi-Person Action Recognition in TOP-VIEW 360^° Videos

Stephen

Liu

Barsopia

2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Action recognition in top-view 360 • videos is an emerging research topic in computer vision. Existing work utilizes a global projection method to transform 360 • video frames to panorama frames for further processing. However, this unwrapping suffers from a problem of geometric distortion i.e., people present near the centre in the 360 • video frames appear highly stretched and distorted in the corresponding panorama frames (observed in 37.5% of the total panorama frames in 360Action dataset). Thus, recognizing the actions of people who are near the centre becomes difficult, thereby affecting the overall action recognition performance. In this work, we overcome the above challenge by utilizing distortion-free person-centric images of the persons near the centre, extracted directly from the input 360 • video frames. We propose a simple yet effective hybrid twostream architecture consisting of a panorama stream and a personcentric stream where outputs from both streams are combined together to detect the overall actions in a video. We perform experiments to validate the efficacy of the proposed method on the recently introduced 360Action dataset and achieve an overall improvement of 2.3% mAP compared to the state-of-the art method and a maximum improvement of 22.7% AP for pickup action, which happens mostly near the centre.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

A Hybrid two-stream approach for Multi-Person Action Recognition in TOP-VIEW 360^° Videos

Stephen

Liu

Barsopia

2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…Considering the attractive performance and straightforward implementation, most existing omnidirectional pedestrian detection methods (Nguyen et al, 2016;Seidel et al, 2019;Li et al, 2019;Duan et al, 2020), as well as ours in the conference paper (Tamura et al, 2019), adopt YOLO as a base detector. YOLO uses pixel-wise dense prediction, which outputs duplicated detection results, and thus requires a suppression postprocess.…”

Section: Object Detectionmentioning

confidence: 99%

“…However, they require a certain amount of computational time to process multiple images transformed from an omnidirectional image, which substantially degrades the detection speed. Duan et al (2020) proposed a rotation-aware pedestrian detector and several omnidirectional pedestrian detection datasets that are annotated with rotated bounding boxes. To predict the angles of the boxes, an angle-aware loss is introduced into YOLOv3.…”

Section: Omnidirectional Pedestrian Detectionmentioning

confidence: 99%

“…To leverage the rotation-aware (Duan et al, 2020) and suppression-free (Carion et al, 2020;Zhu et al, 2021) detection for omnidirectional pedestrian detection, we train Deformable DETR with the angle-aware loss function. We briefly review the overall architecture and loss calculation for training the detector.…”

Section: Overview Of the Detectormentioning

confidence: 99%

“…As a sub-problem of pedestrian detection, omnidirectional pedestrian detection has also been studied for years (Cinaroglu and Bastanlar, 2014;Krams and Kiryati, 2017;Demirkus et al, 2017;Nguyen et al, 2016;Seidel et al, 2019;Tamura et al, 2019;Li et al, 2019;Duan et al, 2020). A major difference between omnidirectional pedestrian detection and the general one is that the appearance of pedestrians tends to be deformed due to the wide angle of view by omnidirectional cameras.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Segmentation-Based Bounding Box Generation for Omnidirectional Pedestrian Detection

Tamura¹,

Yoshinaga²

2021

Preprint

View full text Add to dashboard Cite

We propose a segmentation-based bounding box generation method for omnidirectional pedestrian detection, which enables detectors to tightly fit bounding boxes to pedestrians without omnidirectional images for training. Because the appearance of pedestrians in omnidirectional images may be rotated to any angle, the performance of common pedestrian detectors is likely to be substantially degraded. Existing methods mitigate this issue by transforming images during inference or training detectors with omnidirectional images. However, the first approach substantially degrades the inference speed, and the second approach requires laborious annotations. To overcome these drawbacks, we leverage an existing large-scale dataset, whose segmentation annotations can be utilized, to generate tightly fitted bounding box annotations. We also develop a pseudo-fisheye distortion augmentation method, which further enhances the performance. Extensive analysis shows that our detector successfully fits bounding boxes to pedestrians and demonstrates substantial performance improvement.

show abstract

An Efficient Method for Addressing COVID-19 Proximity Related Issues in Autonomous Shuttles Public Transportation

Tsiktsiris

Lalas

Dasygenis

et al. 2022

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images

Cited by 65 publications

References 21 publications

A Hybrid two-stream approach for Multi-Person Action Recognition in TOP-VIEW 360^° Videos

A Hybrid two-stream approach for Multi-Person Action Recognition in TOP-VIEW 360^° Videos

Segmentation-Based Bounding Box Generation for Omnidirectional Pedestrian Detection

An Efficient Method for Addressing COVID-19 Proximity Related Issues in Autonomous Shuttles Public Transportation

Contact Info

Product

Resources

About

RAPiD: Rotation-Aware People Detection in Overhead Fisheye Images

Cited by 65 publications

References 21 publications

A Hybrid two-stream approach for Multi-Person Action Recognition in TOP-VIEW 360° Videos

A Hybrid two-stream approach for Multi-Person Action Recognition in TOP-VIEW 360° Videos

Segmentation-Based Bounding Box Generation for Omnidirectional Pedestrian Detection

An Efficient Method for Addressing COVID-19 Proximity Related Issues in Autonomous Shuttles Public Transportation

Contact Info

Product

Resources

About

A Hybrid two-stream approach for Multi-Person Action Recognition in TOP-VIEW 360^° Videos

A Hybrid two-stream approach for Multi-Person Action Recognition in TOP-VIEW 360^° Videos