An efficient convolutional neural network for small traffic sign detection

Song, Shijin; Que, Zhiqiang; Hou, Junjie; Du, Shaofu; Song, Yibing

doi:10.1016/j.sysarc.2019.01.012

Cited by 49 publications

(18 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Figure 7, the size of the original image is 1280 × 720, but the pixels of the traffic sign in the figure are 25 × 23 and 26 × 26 (smaller than 32 × 32) which shows that this dataset is suitable for training small targets. [12]. And we use K-Means clustering to re-cluster the training set to further improve the learning speed.…”

Section: Dataset Our Dataset Comes From Csust Chinesementioning

confidence: 99%

See 1 more Smart Citation

Detecting Small Chinese Traffic Signs via Improved YOLOv3 Method

Zhang

Wang

Hui-lan

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Long-distance detection of traffic signs provides drivers with more reaction time, which is an effective technique to reduce the probability of sudden accidents. It is recognized that the imaging size of far traffic signs is decreasing with distance. Such a fact imposes much challenge on long-distance detection. Aiming to enhance the recognition rate of long-distance small targets, we design a four-scale detection structure based on the three-scale detection structure of YOLOv3 network. In order to reduce the occlusion effects of similar objects, NMS is replaced by soft-NMS. In addition, the datasets are trained and the K-Means method is used to generate the appropriate anchor boxes, so as to speed up the network computing. By using these methods, better experimental results for the recognition of long-distance traffic signs have been obtained. The recognition rate is 43.8 frames per second (FPS), and the recognition accuracy is improved to 98.8%, which is much better than the original YOLOv3.

show abstract

Section: Dataset Our Dataset Comes From Csust Chinesementioning

confidence: 99%

“…In [11], Zuo et al used Faster R-CNN to detect traffic signs with a map of 34.49%. In [12], Song et al proposed a constitutional neural network with a small number of parameters to achieve the detection of traffic signs, and its mAP is 88%.…”

Section: Introductionmentioning

confidence: 99%

Detecting Small Chinese Traffic Signs via Improved YOLOv3 Method

Zhang

Wang

Hui-lan

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…Noh et al [ 27 ] proposed a GAN-based model to detect small objects by generating super-resolution features with the guidance of target features extracted from original images, after which the generated super-resolution features were used to predict small objects. Song et al [ 28 ] presented a lightweight CNN model for mobile platforms to detect small traffic signs, with network cropping and convolutional kernel decomposition techniques applied to reduce parameters.…”

Section: Related Workmentioning

confidence: 99%

Dense-RefineDet for Traffic Sign Detection and Classification

Sun

Wang

et al. 2020

Sensors

View full text Add to dashboard Cite

Detecting and classifying real-life small traffic signs from large input images is difficult due to their occupying fewer pixels relative to larger targets. To address this challenge, we proposed a deep-learning-based model (Dense-RefineDet) that applies a single-shot, object-detection framework (RefineDet) to maintain a suitable accuracy–speed trade-off. We constructed a dense connection-related transfer-connection block to combine high-level feature layers with low-level feature layers to optimize the use of the higher layers to obtain additional contextual information. Additionally, we presented an anchor-design method to provide suitable anchors for detecting small traffic signs. Experiments using the Tsinghua-Tencent 100K dataset demonstrated that Dense-RefineDet achieved competitive accuracy at high-speed detection (0.13 s/frame) of small-, medium-, and large-scale traffic signs (recall: 84.3%, 95.2%, and 92.6%; precision: 83.9%, 95.6%, and 94.0%). Moreover, experiments using the Caltech pedestrian dataset indicated that the miss rate of Dense-RefineDet was 54.03% (pedestrian height > 20 pixels), which outperformed other state-of-the-art methods.

show abstract

“…However, because the deployment of deep neural network in mobile platforms is time-consuming and has large computation, it is challenging to detect the traffic signs in mobile devices. Therefore, methods [13], [14] based on light-weight network designed by model compression to reduce the calculation of network parameters, achieving the real-time traffic sign detection.…”

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

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

An efficient convolutional neural network for small traffic sign detection

Cited by 49 publications

References 7 publications

Detecting Small Chinese Traffic Signs via Improved YOLOv3 Method

Detecting Small Chinese Traffic Signs via Improved YOLOv3 Method

Dense-RefineDet for Traffic Sign Detection and Classification

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

Contact Info

Product

Resources

About