TY - JOUR
T1 - A floating-waste-detection method for unmanned surface vehicle based on feature fusion and enhancement
AU - Li, Yong
AU - Wang, Ruichen
AU - Gao, Dongxu
AU - Liu, Zhiyong
N1 - Funding Information:
This research was funded by the Guangxi Science and Technology base and Tlalent Project (Grant No. Guike AD22080043), the Key Laboratories of Sensing and Application of Intelligent Optoelectronic System in Sichuan Provincial Universities (Grant No. ZNGD2206) and Guangxi Science and Technology Program: Guangxi key research and development program (Grant No. Guike AB21220039). Key Laboratcry of AI and Information Processing (Hechi University), Education Department of Guangxi Zhuang Autonomous Region (Grant No. 2022GXZDSY006). The APC was funded by Yong Li.
Publisher Copyright:
© 2023 by the authors.
PY - 2023/11/26
Y1 - 2023/11/26
N2 - Unmanned surface vehicle (USV)-based floating-waste detection presents significant challenges. Due to the water surface’s high reflectivity, there are often light spots and reflections in images captured by USVs. Furthermore, floating waste often consists of numerous small objects that prove difficult to detect, posing a robustness challenge for object-detection networks. To address these issues, we introduce a new dataset collected by USV, FloatingWaste-I, which accounts for the effects of light in various weather conditions, including sunny, cloudy, rainy and nighttime scenarios. This dataset comprises two types of waste: bottles and cartons. We also propose the innovative floating-waste-detection network, YOLO-Float, which incorporates a low-level representation-enhancement module and an attentional-fusion module. The former boosts the network’s low-level representation capability while the latter fuses the highest- and lowest-resolution feature map to improve the model robustness. We evaluated our method by using both the public dataset FloW-img and our FloatingWaste-I dataset. The results confirm YOLO-Float’s effectiveness, with an AP of 44.2% on the FloW-img dataset, surpassing the existing YOLOR, YOLOX and YOLOv7 by 3.2%, 2.7% and 3.4%, respectively.
AB - Unmanned surface vehicle (USV)-based floating-waste detection presents significant challenges. Due to the water surface’s high reflectivity, there are often light spots and reflections in images captured by USVs. Furthermore, floating waste often consists of numerous small objects that prove difficult to detect, posing a robustness challenge for object-detection networks. To address these issues, we introduce a new dataset collected by USV, FloatingWaste-I, which accounts for the effects of light in various weather conditions, including sunny, cloudy, rainy and nighttime scenarios. This dataset comprises two types of waste: bottles and cartons. We also propose the innovative floating-waste-detection network, YOLO-Float, which incorporates a low-level representation-enhancement module and an attentional-fusion module. The former boosts the network’s low-level representation capability while the latter fuses the highest- and lowest-resolution feature map to improve the model robustness. We evaluated our method by using both the public dataset FloW-img and our FloatingWaste-I dataset. The results confirm YOLO-Float’s effectiveness, with an AP of 44.2% on the FloW-img dataset, surpassing the existing YOLOR, YOLOX and YOLOv7 by 3.2%, 2.7% and 3.4%, respectively.
KW - feature enhancement
KW - feature fusion
KW - floating-waste dataset
KW - object detection
KW - unmanned surface vehicle
UR - http://www.scopus.com/inward/record.url?scp=85180732222&partnerID=8YFLogxK
U2 - 10.3390/jmse11122234
DO - 10.3390/jmse11122234
M3 - Article
AN - SCOPUS:85180732222
SN - 2077-1312
VL - 11
JO - Journal of Marine Science and Engineering
JF - Journal of Marine Science and Engineering
IS - 12
M1 - 2234
ER -