Walking pedestrian recognition

Abstract

Abstract-In recent years many methods providing the ability to recognize rigid obstacles -sedans and trucks -have been developed. These methods provide the driver with relevant information. They are able to cope reliably with scenarios on motorways. Nevertheless, not much attention has been given to image processing approaches to increase the safety of pedestrians in urban environments. In this paper a method for the detection, tracking, and final recognition of pedestrians crossing the moving oberserver's trajectory is suggested. A combination of data-and model-driven approaches is realized. The initial detection process is based on a fusion of texture analysis, model-based grouping of, most likely, the geometric features of pedestrians, and inverseperspective mapping (binocular vision). Additionally, motion patterns of limb movements are analyzed to determine initial object hypotheses. The tracking of the quasi-rigid part of the body is performed by different algorithms that have been successfully employed for the tracking of sedans, trucks, motorbikes, and pedestrians. The final classification is obtained by a temporal analysis of the walking process.

Monocular pedestrian recognition using motion parallax

“…Other techniques involve purely temporal cues to model characteristical motion patterns resulting from human gait, in terms of (relative) deviations in the optical flow field [7], [13], [14], or hand-crafted human motion models [5]. Such approaches usually fail to detect static pedestrians, due to the lack of temporal cues on static objects.…”

“…The application of parallax flow allows to focus on static non-planar or moving objects, while at the same time compensating camera ego-motion. Further, this representation seamlessly extends to the detection of static pedestrians, unlike previous approaches which require target motion [5], [7], [13], [14].…”

Pedestrian Detection in Far Infrared Images based on the use of Probabilistic Templates

“…In the GOLD system [3], vertical symmetries are associated with potential pedestrians. In [8] the local image entropy directs the focus-of-attention followed by a model-matching module.…”

“…Motion based approaches use the periodicity of human gait [8], [9], [15], [17], [28] or gait patterns for pedestrian detection [28]. These approaches seems to be more reliable than shape based ones, but they require temporal information and are unable to correctly classify pedestrians that are still or have an unusual gait pattern.…”

IR Pedestrian Detection for Advanced Driver Assistance Systems

“…Several different image processing methods and systems have been developed in the last years, including shape-based methods [5,6], textureand template-based methods [7,8], stereo [9], as well as motion clues [10,11]. All these methods have to overcome the difficulties of different appearances of pedestrians in the visual domain caused mainly by e.g.…”