Analysis of the discriminative generalized Hough transform as a proposal generator for a deep network in automatic pedestrian and car detection

Gabriel, Eric; Schleiss, Michael; Schramm, Hauke; Meyer, Carsten

doi:10.1117/1.jei.27.5.051228

Cited by 8 publications

(2 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sheshkus et al [36] utilize Hough transform for vanishing points detection in the documents. For automatic pedestrian and car detection, Gabriel et al [37] proposed using discriminative generalized Hough transform for proposal generation in edge images, later to further refine the boxes, they fed these proposals to deep networks. In the deep learning era, we are not the first to use a log-polar vote field in a voting-based model.…”

Section: Related Workmentioning

confidence: 99%

HoughNet: Integrating Near and Long-Range Evidence for Bottom-Up Object Detection

Samet

Hiçsönmez

Akbaş

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This paper presents HoughNet, a one-stage, anchor-free, voting-based, bottom-up object detection method. Inspired by the Generalized Hough Transform, HoughNet determines the presence of an object at a certain location by the sum of the votes cast on that location. Votes are collected from both near and long-distance locations based on a log-polar vote field. Thanks to this voting mechanism, HoughNet is able to integrate both near and long-range, class-conditional evidence for visual recognition, thereby generalizing and enhancing current object detection methodology, which typically relies on only local evidence. On the COCO dataset, HoughNet's best model achieves 46.4 AP (and 65.1 AP 50 ), performing on par with the state-of-the-art in bottom-up object detection and outperforming most major one-stage and two-stage methods. We further validate the effectiveness of our proposal in other visual detection tasks, namely, video object detection, instance segmentation, 3D object detection and keypoint detection for human pose estimation, and an additional "labels to photo" image generation task, where the integration of our voting module consistently improves performance in all cases. Code is available at https://github.com/nerminsamet/houghnet.

show abstract

Section: Related Workmentioning

confidence: 99%

HoughNet: Integrating Near and Long-Range Evidence for Bottom-Up Object Detection

Samet

Hiçsönmez

Akbaş

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Sheshkus et al [42] utilize Hough transform for vanishing points detection in the documents. For automatic pedestrian and car detection, Gabriel et al [13] proposed using discriminative generalized Hough transform for proposal generation in edge images, later to further refine the boxes, they fed these proposals to deep networks. In the deep learning era, we are not the first to use a log-polar vote field in a voting-based model.…”

Section: Related Workmentioning

confidence: 99%

HoughNet: Integrating near and long-range evidence for bottom-up object detection

Samet¹,

Hiçsönmez²,

Akbaş³

2020

Preprint

View full text Add to dashboard Cite

This paper presents HoughNet, a one-stage, anchor-free, votingbased, bottom-up object detection method. Inspired by the Generalized Hough Transform, HoughNet determines the presence of an object at a certain location by the sum of the votes cast on that location. Votes are collected from both near and long-distance locations based on a logpolar vote field. Thanks to this voting mechanism, HoughNet is able to integrate both near and long-range, class-conditional evidence for visual recognition, thereby generalizing and enhancing current object detection methodology, which typically relies on only local evidence. On the COCO dataset, HoughNet's best model achieves 46.4 AP (and 65.1 AP50), performing on par with the state-of-the-art in bottom-up object detection and outperforming most major one-stage and two-stage methods. We further validate the effectiveness of our proposal in another task, namely, "labels to photo" image generation by integrating the voting module of HoughNet to two different GAN models and showing that the accuracy is significantly improved in both cases. Code is available at https://github.com/nerminsamet/houghnet.

show abstract

Vision-based Road Segmentation for Intelligent Vehicles using Deep Convolutional Neural Networks

Öztel

2021

2021 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)

View full text Add to dashboard Cite

Analysis of the discriminative generalized Hough transform as a proposal generator for a deep network in automatic pedestrian and car detection

Cited by 8 publications

References 44 publications

HoughNet: Integrating Near and Long-Range Evidence for Bottom-Up Object Detection

HoughNet: Integrating Near and Long-Range Evidence for Bottom-Up Object Detection

HoughNet: Integrating near and long-range evidence for bottom-up object detection

Vision-based Road Segmentation for Intelligent Vehicles using Deep Convolutional Neural Networks

Contact Info

Product

Resources

About