This paper proposes an adaptive cross-window stereo camera distance estimation technology which is a low complexity disparity algorithm and high efficient parallelized, which includes Adaptive Cross Window Distance Estimation (ACWDE) and disparity-based erosion. The proposed algorithm reduces the computation time by changing the aggregation window shape, which calculates color and texture of 13 pixels to generate a pixel disparity. The computation time is speeded up 2.97 times compares to the original system. By integrating ACWDE with voting filter, median filter and proposed disparity-based erosion, which erodes noise only for nearer disparity level, good enough disparity map can be generated, which 10.38% average error rate in Middlebury dataset. This proposed system can generate quality disparity map according to dual VGA resolution videos at 11fps through down-scaling disparity estimation. The proposed ACWDE algorithm also facilities moving object detection and can be adopted in various applications by changing the baseline of stereo camera to set the distance estimation range.