Deep Learning for Perception and Recognition Based on Sensor Data: Methods and Applications, 2nd Edition

Dear Colleagues,

The rapid advancement of deep learning technology has brought about transformative breakthroughs in interpreting data from a multitude of sensors, revolutionizing perception and recognition systems across a wide range of applications. In addition to driving innovation in industrial sectors, it has opened up significant opportunities in fields such as intelligent transportation, smart cities, healthcare, and robotics, where perception is fundamentally built upon heterogeneous sensor streams from cameras, LiDAR, radar, inertial measurement units (IMUs), and beyond.

Deep learning significantly enhances the accuracy and robustness of sensor-based perception and recognition systems through hierarchical feature extraction in multilayer neural networks, achieving remarkable results in areas such as sensor fusion, vision-based inspection, spectral data analysis, and point cloud processing. By training on large volumes of sensor data, deep learning algorithms are able to automatically learn complex feature representations and efficiently recognize patterns directly from raw or minimally processed sensor inputs.

As application scenarios grow more complex and sensor data become increasingly diverse (e.g., multimodal, high-dimensional, and streaming), deep learning models continue to face significant challenges in solving real-world perception and recognition problems. These challenges include ensuring model generalization when dealing with inherently noisy, imbalanced, or limited sensor data; enhancing performance through self-supervised, few-shot, or transfer learning in cases of insufficient labeled sensor data; seamlessly integrating information across different sensor scales, dimensions, and modalities; and developing explainable and trustworthy perception and recognition systems for high-risk applications.

This Special Issue seeks to highlight advanced research in deep learning for sensor-based perception and recognition. Submitted papers should clearly present novel contributions, whether in general methodologies or innovative applications, addressing any of the following or related topics:

• Deep Learning for Novel Sensor Modalities
• Multimodal and Cross-Modal Sensor Fusion
• Efficient Deep Learning Models for Edge and Sensor Networks
• Self-Supervised/Semi-Supervised Learning for Sensor Data
• Point Cloud and 3D Range Data Processing
• Time-Series and Signal Processing for Sensors
• Explainable AI (XAI) for Sensor-Based Systems
• Hardware-Software Co-Design for Sensor Intelligence
• Multi-Sensor Perception for Robotics: Vision and Beyond
• Intelligent Decision-Making Based on Sensor-Driven Perception

Dr. Gaochang Wu
Dr. Zizhu Fan
Dr. Dong Pan
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.