Detecting and localising obstacles in front of a moving vehicle using linear stereo vision

Objects Detection and Tracking Using Points Cloud Reconstructed from Linear Stereo Vision

“…The line-scan cameras based stereo set-up (see Figure 8) is installed on top of a car for periodically acquiring stereo pairs of linear images as the car travels (see Figures 9 and 10) [11,12]. The tilt angle is adjusted so that the optical plane intersects the pavement at a given distance D max in front of the car.…”

“…This temporal constraint will allow ignoring objects generated erroneously from the stereo matching process. The temporal constraint consists in associating a minimum lifetime to each object [12]. In our case, we set the minimum lifetime to 5 successive detections: when an object is not detected during 5 successive frames, we estimate that it disappears.…”

“…Linear stereovision refers to the use of linear cameras providing line-images of the scene [10][11][12]. Indeed, the field of view of this type of cameras is reduced to a plane (see Figure 2).…”

Stereo kamera sisteminde aykırılık haritaları yardımıyla nesne uzaklıklarının tespit edilmesi

“…Araçların önündeki engellerin tespit edilmesi problemini ele alan çalışmalarda çeşitli düzenekler kullanılmıştır. Burie, Bruyelle ve Postaire'nin [2] çalışmalarında araç üzerine 2 adet lineer kamera koyulması ile sıralı stereo görüntüler elde edilmiş, sağ ve sol görüntünün yeni bir kenar bulma prosedürü ile analizi gerçekleştirilmiştir. Ayrıca kurulan sistem gerçek trafikte test edilmiştir.…”

Global Techniques for Edge based Stereo Matching

“…In order to improve this basic approach, it has been proposed to explore the edges of the two linear images sequentially, from one end to the other. A majority of candidate edges can be matched without ambiguities by means of this scheme, performed forward and backward (Burie et al, 1995). However, this sequential procedure can leave some unmatched edges, and may lead to false matches, which are difficult to identify.…”