Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network

Wang, Wenhai; Xie, Enze; Song, Xiaoge; Zang, Yuhang; Wang, Wenjia; Lü, Tong; Yu, Gang; Shen, Chunhua

doi:10.48550/arxiv.1908.05900

Cited by 6 publications

(4 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CBS structure consists of the convolutional layers, batch normalization (BN), and SiLU [33] activation function, the SPPF structure transmits the input information through several MaxPool layers which sizes are 5×5 sequentially. A feature pyramid structure based on PANet [34] is used in the neck subnetwork, which locates between the detection subnetwork and backbone subnetwork. In this layer, strong semantic characteristics are conveyed from the top down while strong location features are transmitted from the bottom up.…”

Section: Methodsmentioning

confidence: 99%

A Fast and Accurate Small Target Detection Algorithm Based on Feature Fusion and Cross-Layer Connection Network for the SAR Images

Sun,

Li,

Chen

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Target detection technology has been greatly improved for the synthetic aperture radar (SAR) images recently, due to the advancement in deep learning (DL) domain. However, because of the existence of clutter in the SAR images, it's still a challenge to detect small targets with high accuracy and low computational complexity. To solve this problem, a detection algorithm based on feature fusion and cross-layer connection (FFCLC) network is proposed in this paper. Firstly, the attention feature fusion (AFF) is applied to improve the feature fusion ability for the small targets through allocating weights to various feature maps adaptively. Meanwhile, the depthwise separable convolution (DW-Conv) is used to reduce the computational complexity caused by the increasement of network layers. Then, a cross-layer connection (Cross-Connect) submodule is proposed to fuse shallow features with deep features further. Finally, a multi-scale target detection (Multi-Detect) submodule is designed to improve the detection ability for the small targets. We compare the proposed algorithm with the other representative methods on the SAR-Ship-Dataset and SSDD, quantitative evaluations show that our proposed algorithm's can reach the highest computational efficiency. Therefore, because of the superior performance in terms of accuracy and efficiency, the algorithm proposed in this paper is more suitable to detect small targets for the SAR images.

show abstract

Section: Methodsmentioning

confidence: 99%

A Fast and Accurate Small Target Detection Algorithm Based on Feature Fusion and Cross-Layer Connection Network for the SAR Images

Sun,

Li,

Chen

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…(2) YOLOv5s neck network The neck network of YOLOv5s follows the structure of a feature pyramid network (FPN) [54] and path aggregation network (PAN) [55], as shown in figure 4, and is mainly composed of convolutional, upsampling, and concat layers, as well as a C3 module. FPN constructs feature pyramids of all scales using a top-down process.…”

Section: Datasetsmentioning

confidence: 99%

CaSnLi-YOLO: construction site multi-target detection method based on improved YOLOv5s

Hao,

Zhang,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

To address the problem of the frequent occurrence of major casualties during construction, a lightweight multi-target detection model based on YOLOv5s, named CaSnLi-YOLO, was proposed for the detection of multiple targets consisting of construction workers and various mechanical equipment at construction sites. In this study, the introduction of the Coordinate Attention (CA) mechanism along with DWConv and C3Ghost based on GhostNet, enhanced the expression and detection accuracy of the model, effectively reducing the number of parameters. Considering the environmental characteristics of construction sites, a detection box filtering strategy based on Soft Non-Maximum Suppression (Soft-NMS) was employed, to effectively alleviate the issue of missed detections of occluded targets. Experimental results demonstrate the significant superiority of the proposed CaSnLi-YOLO over current mainstream detection models, such as faster region-based convolutional neural network (Faster R-CNN) and single-shot detector (SSD). The proposed CaSnLi-YOLO has a parameter number of 5.96×106, which is 15.2% less than that of the original YOLOv5s model, further improving precision, recall rate, mAP@0.5, and mAP@0.5:0.95 by 0.6%, 0.6 %, 0.2%, and 2.3%, respectively. The improved YOLOv5s model proposed in this study achieved significant improvements in multi-target detection at construction sites. The model demonstrated effective enhancements while significantly reducing parameter count and is expected to be deployed in small-edge devices for real-time security monitoring at construction sites.

show abstract

“…Neck: The Neck component is in charge of fusing the backbone features and improving their representational power. For its Neck section, YOLOv5 employs the Feature Pyramid Network (FPN [28]) and Pixel Aggregation Network (PAN [29]) structures. The FPN structure transmits semantic information from top to bottom via an upsampling operation, while the PAN structure transmits location information from bottom-to-top via a downsampling operation.…”

Section: Yolov5mentioning

confidence: 99%

Improved YOLOv5-Based Lightweight Object Detection Algorithm for People with Visual Impairment to Detect Buses

2023

View full text Add to dashboard Cite

Object detection is crucial for individuals with visual impairment, especially when waiting for a bus. In this study, we propose a lightweight and highly accurate bus detection model based on an improved version of the YOLOv5 model. We propose integrating the GhostConv and C3Ghost Modules into the YOLOv5 network to reduce the number of parameters and floating-point operations per second (FLOPs), ensuring detection accuracy while reducing the model parameters. Following that, we added the SimSPPF module to replace the SPPF in the YOLOv5 backbone for increased computational efficiency and accurate object detection capabilities. Finally, we developed a Slim scale detection model by modifying the original YOLOv5 structure in order to make the model more efficient and faster, which is critical for real-time object detection applications. According to the experimental results, the Improved-YOLOv5 outperforms the original YOLOv5 in terms of the precision, recall, and mAP@0.5. Further analysis of the model complexity reveals that the Improved-YOLOv5 is more efficient due to fewer FLOPS, with fewer parameters, less memory usage, and faster inference time capabilities. The proposed model is smaller and more feasible to implement in resource-constrained mobile devices and a promising option for bus detection systems.

show abstract

Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network

Cited by 6 publications

References 46 publications

A Fast and Accurate Small Target Detection Algorithm Based on Feature Fusion and Cross-Layer Connection Network for the SAR Images

A Fast and Accurate Small Target Detection Algorithm Based on Feature Fusion and Cross-Layer Connection Network for the SAR Images

CaSnLi-YOLO: construction site multi-target detection method based on improved YOLOv5s

Improved YOLOv5-Based Lightweight Object Detection Algorithm for People with Visual Impairment to Detect Buses

Contact Info

Product

Resources

About