Automatic Person Detection System based on Image Analysis

The Intelligent Systems Laboratory at Universidad Carlos III de Madrid has developed an automatic person detection system based on image analysis that identifies the presence of people in camera-captured images. The solution operates independently of clothing, activity, movement, or physical appearance, and remains robust even when other objects are present in the scene.

Algorithms have been designed to work with both visible-spectrum cameras and long-wave infrared (LWIR) sensors, enabling reliable detection under any lighting conditions. This dual-modality capability allows the system to function effectively in both indoor and outdoor environments, expanding its applicability across diverse operational scenarios.

The technology performs automatic and unsupervised detection and includes temporal trajectory tracking, enabling the reconstruction of movement patterns across video sequences. By combining visible information with body-emitted heat signatures, the system improves detection robustness and continuity, supporting enhanced situational awareness and monitoring capabilities for security and surveillance contexts.

Collaboration sought:
Funding is sought from companies and organizations operating in security, safety, or video-surveillance domains that are interested in advancing, validating, and deploying the automatic person detection system in real operational environments.