Error analysis in a stereo vision-based pedestrian detection sensor for collision avoidance applications

Abstract

This paper presents an analytical study of the depth estimation error of a stereo vision-based pedestrian detection sensor for automotive applications such as pedestrian collision avoidance and/or mitigation. The sensor comprises two synchronized and calibrated low-cost cameras. Pedestrians are detected by combining a 3D clustering method with Support Vector Machine-based (SVM) classification. The influence of the sensor parameters in the stereo quantization errors is analyzed in detail providing a point of reference for choosing the sensor setup according to the application requirements. The sensor is then validated in real experiments. Collision avoidance maneuvers by steering are carried out by manual driving. A real time kinematic differential global positioning system (RTK-DGPS) is used to provide ground truth data corresponding to both the pedestrian and the host vehicle locations. The performed field test provided encouraging results and proved the validity of the proposed sensor for being used in the automotive sector towards applications such as autonomous pedestrian collision avoidance.

Keywords: 3D sensors; automotive industry; computer vision; pedestrian detection; stereo quantization errors.

Figure 1.

(Top left) Low cost stereo vision sensor. (Top right) RTK-DGPS. (Bottom) Experimental vehicle (modified Citröen C4).

Figure 2.

Overview of the stereo vision-based pedestrian detection architecture.

Figure 3.

Pedestrian collision avoidance maneuver.

Figure 4.

Absolute and relative depth estimation errors for a stereo sensor with f = 4 mm and image size of 320 × 240 px, for different baselines.

Figure 5.

Absolute and relative depth estimation errors for a stereo sensor with B = t_x = 400 mm and image size of 320 × 240 px, for different focal lengths.

Figure 6.

Absolute and relative depth estimation error for a stereo sensor with B = t_x = 400 mm and f = 4 mm, for different image sizes.

Figure 7.

Blind frontal range as a function of the focal length, for different baselines. Note that the size of the images has no effect on the size of the blind frontal area.

Figure 8.

Size of the disparity search space as a function of the focal length, for different baselines with images of 320 × 240 px. The disparity search space is computed from 2 m to 30 m.

Figure 9.

Size of the disparity search space as a function of the focal length, for different image sizes, with a baseline of B = t_x = 400 mm. The disparity search space is computed from 2 m to 30 m.

Figure 10.

Experimental setup. The RTK-DGPS is used as ground truth data from both pedestrian position and vehicle position. The stereo sensor provides host-to-pedestrian sTTC measurements.

Figure 11.

(a) RTK-DGPS stationary position in a 90 s run. (b) RTK-DGPS distance to its mean along time.

Figure 12.

Pedestrian collision avoidance maneuvers at different speeds.

Figure 13.

Stereo Host-to-Pedestrian (H2P) distance measurements and their accuracy and RTK-DGPS H2P distance (ground truth) at (a) 10 km/h, (b) 20 km/h and (c) 30 km/h.

Figure 14.

RTK-DGPS TTC, stereo TTC and absolute error in avoidance experiments performed at (a) 10 km/h, (b) 20 km/h and (c) 30 km/h.