Adrian Broadhurst

Learn More
This paper presents a framework for reasoning about the future motion of multiple objects in a road scene. Unlike previous approaches, we do not look for known dangerous configurations of objects, but rather we reason about the future paths of all objects in the scene, and assess their danger. Monte Carlo path planning is used to generate a probability(More)
We present a 3D photography method that generates a texture-mapped three-dimensional model of a scene computed from multi-view calibrated two-dimensional photographs. Our approach first performs probabilistic space carving, which results in a 3D grid of voxel probabilities that describe the likelihood of a voxel existing in the model. We then employ a(More)
This paper presents a prediction and planning framework for analysing the safety and interaction of moving objects in complex road scenes. Rather than detecting speci c, known, dangerous con gurations, we simulate all the possible motion and interaction of objects. This simulation is used to detect dangerous situations, and to select the best path. The best(More)
This paper investigates the use of the Space Carving algorithm with outdoor image sequences, using a lambertian lighting model. A new consistency function is proposed that uses a statistical comparison instead of the voxel centroid sampling that was initially proposed. This is important when there is more detail in the images than can be stored in a voxel(More)
As vision systems become more and more complex there is an increasing need to understand the interaction between the various modules that these systems are composed of. In this paper we attempt to answer the question of how a high-level module can feed back its knowledge to a low-level module to improve the performance of the overall system. In particular(More)
  • 1