Redirigiendo al acceso original de articulo en 16 segundos...
ARTÍCULO
TITULO

B-YOLOX-S: A Lightweight Method for Underwater Object Detection Based on Data Augmentation and Multiscale Feature Fusion

Jun Wang    
Shuman Qi    
Chao Wang    
Jin Luo    
Xin Wen and Rui Cao    

Resumen

With the increasing maturity of underwater agents-related technologies, underwater object recognition algorithms based on underwater robots have become a current hotspot for academic and applied research. However, the existing underwater imaging conditions are poor, the images are blurry, and the underwater robot visual jitter and other factors lead to lower recognition precision and inaccurate positioning in underwater target detection. A YOLOX-based underwater object detection model, B-YOLOX-S, is proposed to detect marine organisms such as echinus, holothurians, starfish, and scallops. First, Poisson fusion is used for data amplification at the input to balance the number of detected targets. Then, wavelet transform is used to perform Style Transfer on the enhanced images to achieve image restoration. The clarity of the images and detection targets is further increased and the generalization of the model is enhanced. Second, a combination of BIFPN-S and FPN is proposed to fuse the effective feature layer obtained by the Backbone layer to enhance the detection precision and accelerate model detection. Finally, the localization loss function of the prediction layer in the network is replaced by EIoU_Loss to heighten the localization precision in detection. Experimental results comparing the B-YOLOX-S algorithm model with mainstream algorithms such as FasterRCNN, YOLOV3, YOLOV4, YOLOV5, and YOLOX on the URPC2020 dataset show that the detection precision and detection speed of the algorithm model have obvious advantages over other algorithm networks. The average detection accuracy mAP value is 82.69%, which is 5.05% higher than the benchmark model (YOLOX-s), and the recall rate is 8.03% higher. Thus, the validity of the algorithmic model proposed in this paper is demonstrated.

Palabras claves

 Artículos similares

       
 
Chenhong Yan, Shefeng Yan, Tianyi Yao, Yang Yu, Guang Pan, Lu Liu, Mou Wang and Jisheng Bai    
Ship-radiated noise classification is critical in ocean acoustics. Recently, the feature extraction method combined with time?frequency spectrograms and convolutional neural networks (CNNs) has effectively described the differences between various underw... ver más

 
Linhua Zhang, Ning Xiong, Wuyang Gao and Peng Wu    
With the exponential growth of remote sensing images in recent years, there has been a significant increase in demand for micro-target detection. Recently, effective detection methods for small targets have emerged; however, for micro-targets (even fewer... ver más
Revista: Information

 
Chenglou Liu, Fangfang Xie and Tingwei Ji    
Formation path planning is a significant cornerstone for unmanned aerial vehicle (UAV) swarm intelligence. Previous methods were not suitable for large-scale UAV formation, which suffered from poor formation maintenance and low planning efficiency. To th... ver más
Revista: Aerospace

 
Zeliang Liu, Rui Zhao, Chenglin Tao, Yuan Wang and Xi Liang    
Lattice structures are characterized by a light weight, high strength, and high stiffness, and have a wide range of applications in the aerospace field. Node stress concentration is a key factor affecting the mechanical performance of lattice structures.... ver más
Revista: Aerospace

 
Bochi Guo, Yu Liu, Hui Zhou, Wei Yan and Shuanggen Zhang    
Automatic modulation recognition (AMR) provides excellent performance advantages over conventional algorithms and plays a key role in modern communication. However, a general challenge is that the channel errors greatly deteriorate the classification cap... ver más
Revista: Applied Sciences