Autonomous in situ training of classification modules in real-time vision systems and its application to pedestrian recognition

Pattern Recognition Letters

Volumn 23, Issue 11, 2002, Pages 1263-1270

  Wöhler, Christian ^a  

^a DAIMLER AG   (Germany)

Author keywords

Classification; In situ training; Pedestrian recognition; Real time vision

Indexed keywords

ALGORITHMS; CLASSIFICATION (OF INFORMATION); HUMAN COMPUTER INTERACTION; OBJECT RECOGNITION;

PEDESTRIAN RECOGNITION;

COMPUTER VISION;

IMAGE CLASSIFICATION;

EID: 0036721928     PISSN: 01678655     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-8655(02)00065-X     Document Type: Article

References (16)

1. Fast object recognition in noisy images using simulated annealing
2. Road traffic sign detection and classification
3. A self-organising multipleview representation of 3D objects
4. Learning invariance from transformation sequences
5. Fast stereo based object detection for stop and go traffic
6. Autonomous driving goes downtown
7. Real-time object detection for smart vehicles
8. Motion-based recognition of pedestrians
9. Hybrid approach for traffic sign recognition
10. Hypothesis verification based on classification at unequal error rates
11. A pattern classification approach to dynamical object detection
12. A trainable pedestrian detection system
13. Optimal unsupervised learning in invariant object recognition
14. Real-time object recognition on image sequences with the adaptable time delay neural network algorithm - Applications for autonomous vehicles