Real-time object detection for "smart" vehicles

Abstract

This paper presents an e cient shape-based object detection method based on Distance Transforms and describes its use for real-time vision on-board vehicles. The method uses a template hierarchy to capture the variety of object shapes; e cient hierarchies can be generated o ine for given shape distributions using stochastic optimization techniques i.e. simulated annealing. Online, matching involves a simultaneous coarse-to-ne approach o ver the shape hierarchy and over the transformation parameters. Very large speedup factors are typically obtained when comparing this approach with the equivalent brute-force formulation; we h a ve measured gains of several orders of magnitudes.We present experimental results on the real-time detection of tra c signs and pedestrians from a moving vehicle. Because of the highly time sensitive nature of these vision tasks, we also discuss some hardwarespeci c implementations of the proposed method as far as SIMD parallelism is concerned.

Fast Human Detection in Surveillance Video

“…In [9], moving pixels are grouped in to blobs and using shape features these blobs are classified in to human or non human objects. Gavrila and philomin compared edge images using chamfer distance for human detection [10]. Mikolajczyk et al [11] parts based human detection method containing detectors for front and side profiles of upper and lower body parts, heads and faces.…”

Accurate Human Detection by Appearance and Motion

“…They use human template to find the marching regions in edge map of the inputting image. [27], [28] are based on this method. [28] proposes a direct template matching approach for global shape-based human detection.…”

“…[27], [28] are based on this method. [28] proposes a direct template matching approach for global shape-based human detection. [27] is developed form this method and use the hierarchical template to reduce the detection time and solve the occlusion problem to some extent.…”

Recognizing Posture in Pictures with Successive Convexification and Linear Programming

“…The edge map contains most of the shape information for an object, and at the same time is not very sensitive to color changes. Edge features have been widely applied in Chamfer (edge-based) matching [18] and shape context [25] matching. We have found that small blocks centered on the edge pixels, of a distance transform image are expressive local features.…”