Pengjie Liu
Papers
1
Total Citations
7
H-Index
1
About
Pengjie Liu has made significant contributions to the field of underwater computer vision and marine robotics, with a focus on enhancing the accuracy and efficiency of autonomous underwater target detection. His key research areas include multi-scale image fusion enhancement, lightweight deep learning architectures, and real-time object detection for remotely operated vehicles (ROVs). In his highly cited 2024 work, Liu pioneered a novel method that integrates multi-scale fusion image enhancement with an improved YOLOv5s lightweight model, directly addressing the persistent challenges of low-quality underwater imagery, high computational demands, and inadequate detection precision. By developing a framework that first enhances degraded underwater images and then employs a streamlined detection network, his research enables more reliable perception in turbid, low-visibility marine environments. This work has garnered 7 citations in a short period, reflecting its immediate impact on the marine robotics community. Liu's achievements are notable for bridging the gap between practical deployment constraints—such as limited onboard processing power—and the need for robust, high-accuracy detection, advancing the capabilities of autonomous systems for marine resource exploration and environmental monitoring.
Research Focus
Key Achievements
Top Papers
- 1