Weather-Aware Object Detection Method for Maritime Surveillance Systems

Chen, Mingkang; Sun, Jianyong; Aida, Kô; Takefusa, Atsuko

doi:10.2139/ssrn.4482179

Cited by 1 publication

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to the YOLOv7 algorithm, the mAP 0.5:0.95 , mAP 0.5 , and AP S of the YOLO-BEV algorithm increases by 2.4%, 2.9%, and 13.4%, respectively, and the FPS rate increases by 30%. Three methods, namely YOLOv5, Fast R-CNN, and DETR, were used in reference [24]. Compared with method 3 in reference [24], all evaluation indexes were improved, among which AP S was increased by 12.7%.…”

Section: Ablation Experimentsmentioning

confidence: 99%

“…Three methods, namely YOLOv5, Fast R-CNN, and DETR, were used in reference [24]. Compared with method 3 in reference [24], all evaluation indexes were improved, among which AP S was increased by 12.7%. Although the method in reference [26] achieves 40 FPS in real-time, the average detection accuracy for small objects is only 0.350.…”

Section: Ablation Experimentsmentioning

confidence: 99%

“…Wang et al [23] solved the problem of an object being submerged by background clutter during the detection and tracking process by adding a channel attention mechanism to the model; however, they did not discuss the detection performance of small objects. Chen et al [24] proposed a weather-sensing object-detection method, which realizes high-precision object detection through dynamic selection of machine learning models and regular training, and shows significant performance improvement under rainy and foggy conditions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A High-Precision Detection Model of Small Objects in Maritime UAV Perspective Based on Improved YOLOv5

Yang,

Yin,

Jing

et al. 2023

JMSE

View full text Add to dashboard Cite

Object detection by shipborne unmanned aerial vehicles (UAVs) equipped with electro-optical (EO) sensors plays an important role in maritime rescue and ocean monitoring. However, high-precision and low-latency maritime environment small-object-detection algorithms remain a major challenge. To address this problem, this paper proposes the YOLO-BEV (“you only look once”–“bird’s-eye view”) model. First, we constructed a bidirectional feature fusion module—that is, PAN+ (Path Aggregation Network+)—adding an extremely-small-object-prediction head to deal with the large-scale variance of targets at different heights. Second, we propose a C2fSESA (Squeeze-and-Excitation Spatial Attention Based on C2f) module based on the attention mechanism to obtain richer feature information by aggregating features of different depth layers. Finally, we describe a lightweight spatial pyramid pooling structure called RGSPP (Random and Group Convolution Spatial Pyramid Pooling), which uses group convolution and random channel rearrangement to reduce the model’s computational overhead and improve its generalization ability. The article compares the YOLO-BEV model with other object-detection algorithms on the publicly available MOBDrone dataset. The research results show that the mAP0.5 value of YOLO-BEV reached 97.1%, which is 4.3% higher than that of YOLOv5, and the average precision for small objects increased by 22.2%. Additionally, the YOLO-BEV model maintained a detection speed of 48 frames per second (FPS). Consequently, the proposed method effectively balances the accuracy and efficiency of object-detection in shipborne UAV scenarios, outperforming other related techniques in shipboard UAV maritime object detection.

show abstract

Section: Ablation Experimentsmentioning

confidence: 99%