Enhanced YOLO v3 Tiny Network for Real-Time Ship Detection From Visual Image

Abstract

Different from ship detection from synthetic aperture radar (SDSAR) and ship detection from spaceborne optical images (SDSOI), ship detection from visual image (SDVI) has better detection accuracy and real-time performance, which can be widely used in port management, cross-border ship detection, autonomous ship, safe navigation, and other real-time applications. In this paper, we proposed a new SDVI algorithm, named enhanced YOLO v3 tiny network for real-time ship detection. The algorithm can be used in video surveillance to realize the accurate classification and positioning of six types of ships (including ore carrier, bulk cargo carrier, general cargo ship, container ship, fishing boat, and passenger ship) in real-time. Based on the original YOLO v3 tiny network, we have made the following fine tunings. 1) The preset anchors trained on Seaship annotation data have the similar "dumpy" shape as the normal ships, helping the network to achieve faster and better training; 2) Convolution layer instead of max-pooling layer and expanding the channels of prediction network improve the small target detection ability of the algorithm. 3) Due to the problem that large-scale ships are easily disturbed by the onshore building, complex waves and light on the water surface, we introduced attention module named CBAM into the backbone network, which make the model more focused on the target. The detection accuracy of the proposed algorism is obviously better than that of the original YOLO v3 tiny work. Although it is slightly inferior to the Yolo v3 network, it has faster speed than Yolo v3. However, the proposed algorithm is a better trade-off between real-time performance and detection accuracy, and is more suitable for actual scenes. Compared with the SOAT algorithm in [26], our algorithm has a 9.6% improvement in mAP and a faster speed.

Improved YOLO Based Detection Algorithm for Floating Debris in Waterway

“…The clustering results are sorted by area size as (23,29), (37,34), (26,53), (41, 53), (41, 90), (94, 40), (61, 75) and (78, 135). It can be found that the scales of the prior boxes are quite different, and they are assigned to 76 × 76, 38 × 38, 19 × 19 three feature maps as the prior boxes.…”

“…Teng et al [ 25 ] used a well-known feature extractor model and the YOLOv2 network to detect a concrete crack. Li et al [ 26 ] proposed an enhanced YOLOv3 tiny network for real-time ship detection. Yolo is also widely used in radar images and remote sensing images.…”

High Inclusiveness and Accuracy Motion Blur Real-Time Gesture Recognition Based on YOLOv4 Model Combined Attention Mechanism and DeblurGanv2

“…Firstly, the maximum pooling and mean pooling are performed on the input images, respectively, under the spatial attention module. Then a convolution layer is used to learn the new feature map [26]. where the Max represents the maximum pool processing, the Avg represents the global average pooling processing, the Conv represents the convolution layer,  represents the sigmoid activation function.…”

“…Firstly, the maximum pooling and mean pooling are performed on the input images, respectively, under the spatial attention module. Then a convolution layer is used to learn the new feature map [26].…”

Multi-Dimensional Automatic Detection of Scanning Radar Images of Marine Targets Based on Radar PPInet

“…A region suggestion generator is formed, where features are extracted, and a classifier is used to predict the category of the proposed area. The latter includes YOLO [29], SSD [30], etc., which directly makes classification and prediction for the objects in each position of the feature map. The intelligent algorithm of target detection based on CNN has realized improvement of the detection speed and accuracy, and has great advantages compared with traditional target detection algorithms.…”