David M. DiMeo

A real-time precrash vehicle detection system

This paper presents an in-vehicle real-time monocular precrash vehicle detection system. The system acquires grey level images through a forward facing low light camera and achieves an average detection rate of 10Hz. The vehicle detection algorithm consists of two main steps: multi-scale driven hypothesis generation and appearance-based hypothesis verification. In the multi-scale hypothesis generation step, possible image locations where vehicles might be present are hypothesized. This step uses multi-scale techniques to speed up detection but also to improve system robustness by making system performance less sensitive to the choice of certain parameters. Appearance-base hypothesis verification verifies those hypothesis using Haar Wavelet decomposition for feature extraction and Support Vector Machines (SVMs) for classification. The monocular system was tested under different traffic scenarios (e.g., simply structured highway, complex urban street, varying weather conditions), illustrating good performance.

Predicting a vehicle or pedestrian's next move with neural networks

For a given digitized view of a driving scenario, motion clusters are formed, indicating possible moving object threats to the driver. Recurrent neural networks minimize hopping between clusters and predict a clusters next location. Frequency analysis then categorizes as significant motion, and then as either head-on/away or transverse motion.