VSSA-NET: Vertical Spatial Sequence Attention Network for Traffic Sign Detection

Yuan, Yuan; Xiong, Zhitong; Wang, Qi

doi:10.1109/tip.2019.2896952

Cited by 155 publications

(62 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is hard to use image segmentation in practical application on account of high computational cost. Attention-based detection methods [11], [12] are proposed to reduce the false detection cases arisen from similar false traffic signs. The network structures named Transformer with Multi-Head Attention [19] are designed for the machine translation in Natural Language Processing Transformer network structure discards the recursive unit and Multi-Head Attention structure explores the relationship between input and output in parallel to increase the computational speed.…”

Section: B Motivationmentioning

confidence: 99%

“…The methods [9], [10]based on the image segmentation to detect the traffic signs under complex environment. Some attention-based detection methods [11], [12] gain the ROI from the input image by attention module to fine the features in a large sophisticated background. These two ways enhance the performance of small traffic sign detection and reduce the cases of false detection.…”

Section: Introduction a Backgroundmentioning

confidence: 99%

See 1 more Smart Citation

A Cascaded R-CNN With Multiscale Attention and Imbalanced Samples for Traffic Sign Detection

et al. 2020

View full text Add to dashboard Cite

In recent years, the deep learning is applied to the field of traffic sign detection methods which achieves excellent performance. However, there are two main challenges in traffic sign detection to be solve urgently. For one thing, some traffic signs of small size are more difficult to detect than those of large size so that the small traffic signs are undetected. For another, some false signs are always detected because of interferences caused by the illumination variation, bad weather and some signs similar to the true traffic signs. Therefore, to solve the undetection and false detection, we first propose a cascaded R-CNN to obtain the multiscale features in pyramids. Each layer of the cascaded network except the first layer fuses the output bounding box of the previous one layer for joint training. This method contributes to the traffic sign detection. Then, we propose a multiscale attention method to obtain the weighted multiscale features by dot-product and softmax, which is summed to fine the features to highlight the traffic sign features and improve the accuracy of the traffic sign detection. Finally, we increase the number of difficult negative samples for dataset balance and data augmentation in the training to relieve the interference by complex environment and similar false traffic signs. The data augment method expands the German traffic sign training dataset by simulation of complex environment changes. We conduct numerous experiments to verify the effectiveness of our proposed algorithm. The accuracy and recall rate of our method are 98.7% and 90.5% in GTSDB, 99.7% and 83.62% in CCTSDB and 98.9% and 85.6% in Lisa dataset respectively.

show abstract

Section: B Motivationmentioning

confidence: 99%

Section: Introduction a Backgroundmentioning

confidence: 99%

A Cascaded R-CNN With Multiscale Attention and Imbalanced Samples for Traffic Sign Detection

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Tian et al [36] introduced attention mechanism in traffic sign detection task, and improved detection accuracy by combining local context information. In [37], traffic signs were regarded as small targets in a specific mode, and traffic sign detection was regarded as regional sequence classification and regression task. By using the attention mechanism, the local sequence of the region was modeled explicitly to obtain more context information and improve the detection accuracy.…”

Section: Traffic Sign Detectionmentioning

confidence: 99%

SADANet: Integrating Scale-Aware and Domain Adaptive for Traffic Sign Detection

Liu

Shen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

It holds great implications for large-scale traffic scene understanding, to enable traffic sign detection in real environment. The large intra-category variance in features caused by instances of different spatial scales and appearances are the main problem. In this paper, a traffic sign detection framework using scale-aware and domain adaptive network (SADANet) was proposed, which seamlessly combines a multiscale prediction network (MSPN) with a domain adaptive network (DAN) in a tightly-coupled manner in order to tackle the challenge. Specifically, MSPN is dedicated to extracting the multiscale feature. It utilizes fully, the low-level location and high-level semantic information, and considers the combination of the context information and the instance specific content awareness in the scale transformation. DAN is dedicated to making features domain invariant without enough labeled test data. It aligns the domain distributions from the different scales effectively by leveraging the mapping relationship between the image representation and the multiscale features. Experimental results show that the SADANet is effective in traffic sign detection task and is also competitive when compared with the state-of-the-art methods. INDEX TERMS Adaptive feature weighting, domain adaptation, multiscale feature, traffic sign detection.

show abstract

“…This algorithm can detect more accurate road regions than other traditional methods, and the use of location prior can promote the detection performance effectively. In 2019, Yuan et al [20] presented an end-to-end deep learning method for traffic sign detection in complex environments. The algorithm not only utilizes the densely connected deconvolution layer and frequency hopping connection but also proposes a vertical spatial sequence attention module to obtain more context information to achieve better detection performance.…”

Section: Introductionmentioning

confidence: 99%

A Systematic Algorithm for Moving Object Detection with Application in Real-Time Surveillance

Cui

Créput

2020

SN COMPUT. SCI.

View full text Add to dashboard Cite

Moving object detection and tracking from video sequences are a relevant research field since it can be used in many applications. While detection allows to return object shapes discovered in the image, tracking aims to individually identify and estimate individual trajectories of detected objects over time. Hence, detection can have a crucial impact on the overall tracking process. This paper focuses on detection. Currently, one of the leading detection algorithms includes frame difference method (FD), background subtraction method (BS), and optical flow method. Here, we present a detection algorithm based on the first two approaches since it is very adequate for fast real-time treatments, whereas optical flow has higher computation cost due to a dense estimation. A combination of FD and BS with Laplace filters and edge detectors is a way to achieve sparse detection fast. Thus, a main proposed contribution is the achievement of a systematic detection algorithm for moving target detection with a more elaborated combination of basic procedures used in real-time surveillance. Experimental results show that the proposed method has higher detection accuracy and better noise suppression than the current methods for standard benchmark datasets.

show abstract

VSSA-NET: Vertical Spatial Sequence Attention Network for Traffic Sign Detection

Cited by 155 publications

References 41 publications

A Cascaded R-CNN With Multiscale Attention and Imbalanced Samples for Traffic Sign Detection

A Cascaded R-CNN With Multiscale Attention and Imbalanced Samples for Traffic Sign Detection

SADANet: Integrating Scale-Aware and Domain Adaptive for Traffic Sign Detection

A Systematic Algorithm for Moving Object Detection with Application in Real-Time Surveillance

Contact Info

Product

Resources

About