This book focuses on multimodal collaborative perception—a cornerstone for unmanned systems. As connected vehicles, autonomous driving, and UAV-based monitoring continue to evolve, the ability to integrate diverse sensor data into reliable, real-time situational awareness becomes crucial. This book speaks directly to researchers, graduate students, and professionals who want to understand both the technical foundations and practical applications of collaborative perception.
Structured to bridge theory and practice, the book offers a comprehensive exploration that begins with sensor principles and preprocessing, advances through state estimation, collaborative object detection, tracking, and localization, and culminates in real-world applications in autonomous driving and UAV monitoring. Readers will discover how classical models such as Kalman filtering merge with cutting-edge deep learning techniques, how multimodal data fusion enhances perception under complex conditions, and how digital twin integration, edge computing, and privacy-preserving learning shape the future of the field.
By reading this book, audiences will gain not only a thorough understanding of multimodal sensor technologies but also insights into system-level design and deployment challenges. The book’s unique blend of systematic engineering perspective, algorithmic rigor, and forward-looking research directions makes it stand out as both a textbook and a reference. A background in computer science, electrical engineering, or related fields will help readers maximize its value, but the clear structure also supports learners entering the domain.
Table of Contents:
.- Introduction to Multimodal Collaborative Perception.
.- Multi-source Sensors for Multimodal Collaborative Perception.
.- Information Preprocessing for Multimodal Collaborative Perception.
.- State Estimation for Multimodal Collaborative Perception.
.- Multimodal Collaborative Object Detection.
.- Multimodal Collaborative Object Tracking.
.- Multimodal Collaborative Object Localization.
.- Multimodal Collaborative Perception for Autonomous Driving.
.- Multimodal Collaborative Perception for UAV-based Traffic Monitoring.
.- Future Work of Multimodal Collaborative Perception.
About the Author :
Binglu Wang received his Ph.D. in Control Science and Engineering from Northwestern Polytechnical University (NWPU) in 2021 and currently serves as a Professor at the School of Astronautics, NWPU. His research focuses on multimodal sensor fusion, 3D object detection, semantic segmentation, object tracking, and online cross-sensor calibration, with broad applications in autonomous driving, unmanned systems, and remote sensing. He has published a series of influential papers in leading journals such as IEEE TPAMI, TCSVT, TGRS, and TMM, contributing core methodologies for multimodal perception, weakly supervised learning, and multi-source information integration. He has led and participated in multiple national and provincial research projects, including the National Natural Science Foundation of China Youth Program and key projects from provincial R&D initiatives and State Key Laboratories. His work has been recognized through competitive research funding and his active roles across multiple academic institutions. With strong expertise in multimodal perception and cross-domain sensing, Professor Wang provides essential theoretical and technical contributions to the development of collaborative perception technologies for unmanned systems, forming a central pillar of this monograph.
