Evaluation of daylight and thermal infra-red based detection for platooning vehicles

Abstract

The research project "SafeCon" tackles the problem of the safety in military transport missions. In such missions people can be killed by attacks or natural dangers, for example avalanches. To reduce the number of involved people in transport missions, SafeCon tries to reduce the number of requied personnel by automating each transporter.The aim of SafeCon is the realisation of a semi-autonomous truck convoy. The destruction of one vehicle within the convoy causes financial losses and spares human lives. Further, the vehicles must not be armoured. This reduces both load capacity and costs. For an autonomous behaviour, each truck must be able to follow the vehicle ahead. Because of that, each vehicle must be able to recognise the leading vehicle. This is realised with a computer visiondetection system. To enable an autonomous behaviour in all weather conditions a thermal infra-red camera system is implemented to detect objects based on their heat signature. Different to other approaches, this paper discusses the implementation of an AdaBoost based detection for thermal infra-red image material. The evaluation of our approach compares a thermal infra-red and a visible-light detection. Ourexperiments prove that the thermal infra-red detection is comparable with visible-light detection. Copyright © (2012) by Danube Adria Association for Automation and Manufacturing (DAAAM).