Xinman Zhang
Papers
2
Total Citations
24
H-Index
2
About
Xinman Zhang is a researcher advancing the field of intelligent waste management through deep learning and multi-modal sensing. Their work focuses on developing efficient computer vision systems for detecting and classifying waste in challenging environments, from urban pavements to underwater ecosystems. Zhang’s most-cited paper, “Multi-modal deep learning networks for RGB-D pavement waste detection and recognition” (2024, 20 citations), introduces a novel framework that fuses color and depth data to improve waste identification accuracy in cluttered street scenes—a critical step toward automated urban sanitation. Complementing this, their study “Lightweight deep learning model for underwater waste segmentation based on sonar images” (2024, 4 citations) tackles the pressing issue of marine debris by designing a compact neural network capable of real-time waste segmentation from sonar imagery, enabling deployment on resource-limited underwater robots. By prioritizing both performance and computational efficiency, Zhang’s contributions address real-world deployment constraints while maintaining high detection precision. Their work not only demonstrates the power of multi-modal learning but also highlights a commitment to environmental sustainability, offering scalable AI solutions for waste monitoring across diverse and difficult terrains.
Research Focus
Key Achievements
Top Papers
- 1
- 2