Moving object detection task can be solved by the background subtraction algorithm if the camera is fixed. However, because the background moves, detecting moving objects in a moving car is a difficult problem. There were attempts to detect moving objects using LiDAR or stereo cameras, but when the car moved, the detection rate decreased. We propose a moving object detection algorithm using an object motion reflection model of motion vectors. The proposed method first obtains the disparity map by searching the corresponding region between stereo images. Then, we estimate road by applying v-disparity method to the disparity map. The optical flow is used to acquire the motion vectors of symmetric pixels between adjacent frames where the road has been removed. We designed a probability model of how much the local motion is reflected in the motion vector to determine if the object is moving. We have experimented with the proposed method on two datasets, and confirmed that the proposed method detects moving objects with higher accuracy than other methods.

People counting in surveillance cameras is a key technology for understanding the flow population and generating heat maps. In recent years, people detection performance has been greatly improved with the development of object detection algorithms using deep learning. However, in places where people are crowded, the detection rate is low as people are often occluded by other people. We proposed a people-counting method using a stereo camera to resolve the non-detection problem due to the occlusion. We applied stereo matching to extract the depth image and convert the camera view to top view using depth information. People were detected using a height map and an occupancy map, and people were tracked and counted using a Kalman filter-based tracker. We operated the proposed method on the NVIDIA Jetson TX2 to check the real-time operation possibility on the embedded board. Experimental results showed that the proposed method had higher accuracy than the existing methods and that real-time processing is possible.

Disparity Refinement near the Object Boundaries for Virtual-View Quality Enhancement Stereo matching;Optical flow;Occlusion regions;Texture component; Stereo matching algorithm is usually used to obtain a disparity map from a pair of images. However, the disparity map obtained by using stereo matching contains lots of noise and error regions. In this paper, we propose a virtual-view synthesis algorithm using disparity refinement in order to improve the quality of the synthesized image. First, the error region is detected by examining the consistency of the disparity maps. Then, motion information is acquired by applying optical flow to texture component of the image in order to improve the performance. Then, the occlusion region is found using optical flow on the texture component of the image in order to improve the performance of the optical flow. The refined disparity map is finally used for the synthesis of the virtual view image. The experimental results show that the proposed algorithm improves the quality of the generated virtual-view.

본 논문에서는 외삽으로 가상 시점 영상 생성 시에 발생하는 홀 영역을 효과적으로 채우는 VST 기반의 홀 채움 기법을 제안한다. 기존의 VST 기법은 스테레오 영상을 이용하여 내삽 영상을 생성한다. 가상 시점 생성 시 발생하는 홀 영역을 채우기 위해 시점, 공간적, 시간적 유사성을 가지는 8개의 주변 영상을 탐색한다. 하지만 탐색하는 영상의 개수가 많을 뿐만 아니라 각각의 영상을 풀 서치 방식으로 탐색하기 때문에 속도가 매우 느리다는 단점을 가지고 있다. 외삽 시점에 적용하는 경우에는 내삽 시점보다 홀 영역이 더 많이 생성되기 때문에 VST 기법을 적용하면 시간이 더 많이 소요된다. 따라서 본 논문에서는 외삽 영상 생성 시 검색 범위를 줄여 계산량을 줄이는 동시에 성능은 유지하는 VST 기반의 홀 채움 기법을 제안한다. 먼저 참조 영상의 사용 통계를 분석하여 참조 영상의 개수를 줄였다. 두 번째로 참조 영상에서 블록 탐색 시 n-step 블록 탐색 기법을 적용하였다. 실험을 통해 제안하는 기법이 VST 기법에 비해 속도는 약 8.5배, PSNR은 약 0.78dB 상승한 것을 확인하였다.