A new transform is presented that utilizes local radial symmetry to highlight points of interest within a scene. Its lowcomputational complexity and fast runtimes makes this method well-suited for real-time vision applications. The performance of the transform is demonstrated on a wide variety of images and compared with leading techniques from the literature. Both as a facial feature detector and as a generic region of interest detector the new transform is seen to offer equal or superior performance to contemporary techniques at a relatively low-computational cost. A real-time implementation of the transform is presented running at over 60 frames per second on a standard Pentium III PC.

To build smart human interfaces, it is necessary for a system to know a user's intention and point of attention. Since the motion of a person's head pose and gaze direction are deeply related with his/her intention and attention, detection of such information can be utilized to build natural and intuitive interfaces.In this paper, we describe our real-time stereo face tracking and gaze detection system to measure head pose and gaze direction simultaneously. The key aspect of our system is the use of real-time stereo vision together with a simple algorithm which is suitable for real-time processing. Since the 3D coordinates of the features on a face can be directly measured in our system, we can significantly simplify the algorithm for 3D model fitting to obtain the full 3D pose of the head compared with conventional systems that use monocular camera. Consequently we achieved a non-contact, passive, real-time, robust, accurate and compact measurement system for head pose and gaze direction.

No abstract

Abstract-Algorithms for classifying road signs have a high computational cost per pixel processed. A promising approach to real-time sign detection is to reduce the number of pixels to be classified as being a particular sign to a minimum by some form of sign detection on the image using less time expensive algorithms. In this paper, we adapt the fast radial symmetry detector to the image stream from a camera mounted in a car eliminate almost all non-sign pixels from the image stream. We then are able to apply normalised cross-correlation to classify the signs. This method is suitable for circular signs only; we apply it to Australian speed signs in this paper. Our results show that it is robust to a broad range of lighting conditions. Also, as the method is fast, there is no need to make unrealistically strict assumptions about image structure.

One of the more startling eflects of road related accidents is the economic and social burden they muse. Between 750,000 and 880,000 people died globally in mad related accidents in 1999 alone, with an estimated cost of US518 billion 1111. One way of combating this problem is to develop Intelligent Vehicles that are selfaware and act to inmase the safety of the tmnsportation system. This paper presents the development and applicotion of a novel multiple-cue visual lane tmcking system for research into Intelligent Vehicles (IV). Particle jiltering and cue fusion technologies J o n the basis ofthe lane tmcking system which robustly handles seueml of the problems faced by previous lane tmcking system such (IS shadows on the mad, unreliable lane markings. dmmatic lighting changes and discontinuous changes in mad chamcteristics and types. Ezperimental results of the lane tracking system running at 15Hz will be discusaed, focusing on the particle flter and cue fusion technology used.