Presence Of Camera Motion Research Articles

Exploration of motion inhibition for the suppression of false positives in biologically inspired small target detection algorithms from a moving platform

Detecting small moving targets against a cluttered background in visual data is a challenging task. The main problems include spatio-temporal target contrast enhancement, background suppression and accurate target segmentation. When targets are at great distances from a non-stationary camera, the difficulty of these challenges increases. In such cases the moving camera can introduce large spatial changes between frames which may cause issues in temporal algorithms; furthermore targets can approach a single pixel, thereby affecting spatial methods. Previous literature has shown that biologically inspired methods, based on the vision systems of insects, are robust to such conditions. It has also been shown that the use of divisive optic-flow inhibition with these methods enhances the detectability of small targets. However, the location within the visual pathway the inhibition should be applied was ambiguous. In this paper, we investigated the tunings of some of the optic-flow filters and use of a nonlinear transform on the optic-flow signal to modify motion responses for the purpose of suppressing false positives and enhancing small target detection. Additionally, we looked at multiple locations within the biologically inspired vision (BIV) algorithm where inhibition could further enhance detection performance, and look at driving the nonlinear transform with a global motion estimate. To get a better understanding of how the BIV algorithm performs, we compared to other state-of-the-art target detection algorithms, and look at how their performance can be enhanced with the optic-flow inhibition. Our explicit use of the nonlinear inhibition allows for the incorporation of a wider dynamic range of inhibiting signals, along with spatio-temporal filter refinement, which further increases target-background discrimination in the presence of camera motion. Extensive experiments shows that our proposed approach achieves an improvement of 25% over linearly conditioned inhibition schemes and 2.33 times the detection performance of the BIV model without inhibition. Moreover, our approach achieves between 10 and 104 times better detection performance compared to any conventional state-of-the-art moving object detection algorithm applied to the same, highly cluttered and moving scenes. Applying the nonlinear inhibition to other algorithms showed that their performance can be increased by up to 22 times. These findings show that the application of optic-flow- based signal suppression should be applied to enhance target detection from moving platforms. Furthermore, they indicate where best to look for evidence of such signals within the insect brain.

Topic-based Video Analysis

Manual processing of a large volume of video data captured through closed-circuit television is challenging due to various reasons. First, manual analysis is highly time-consuming. Moreover, as surveillance videos are recorded in dynamic conditions such as in the presence of camera motion, varying illumination, or occlusion, conventional supervised learning may not work always. Thus, computer vision-based automatic surveillance scene analysis is carried out in unsupervised ways. Topic modelling is one of the emerging fields used in unsupervised information processing. Topic modelling is used in text analysis, computer vision applications, and other areas involving spatio-temporal data. In this article, we discuss the scope, variations, and applications of topic modelling, particularly focusing on surveillance video analysis. We have provided a methodological survey on existing topic models, their features, underlying representations, characterization, and applications in visual surveillance’s perspective. Important research papers related to topic modelling in visual surveillance have been summarized and critically analyzed in this article.

Saliency-based dense trajectories for action recognition using low-rank matrix decomposition

Dense trajectory methods have recently been proved to be successful in recognizing actions in realistic videos. However, their performance is still limited due to the uniform dense sampling, which does not discriminate between action-related areas and background. This paper proposes to improve the dense trajectories for recognizing actions captured in realistic scenes, especially in the presence of camera motion. Firstly, based on the observation that the motion in action-related areas is usually much more irregular than the camera motion in background, we recover the salient regions in a video by implementing low-rank matrix decomposition on the motion information and use the saliency maps to indicate action-related areas. Considering action-related regions are changeable but continuous with time, we temporally split a video into subvideos and compute the salient regions subvideo by subvideo. In addition, to ensure spatial continuity, we spatially divide a subvideo into patches and arrange the vectorized optical flow of all the spatial patches to collect the motion information for salient region detection. Then, after the saliency maps of all subvideos in a video are obtained, we incorporate them into dense tracking to extract saliency-based dense trajectories to describe actions. To evaluate the performance of the proposed method, we conduct experiments on four benchmark datasets, namely, Hollywood2, YouTube, HMDB51 and UCF101, and show that the performance of our method is competitive with the state of the art.

시공간 정합을 이용한 비디오 시퀀스에서의 가려진 객체의 복원

비디오 복원(video completion) 기술은 비디오 영상에서 색상 정보가 없는 픽셀에 적절한 색을 채워 영상을 복원하는 기술이다. 본 논문에서는 움직이는 물체가 서로 교차하는 비디오 영상에서 원하지 않는 물체를 제거하고 이때 발생한 영상 홀(image hole)을 채우는 비디오 복원 기술을 제안한다. 움직이는 카메라에서 획득한 비디오 영상에서 이동하는 두 물체 중 카메라와 가까운 물체를 제거함으로써 가려진 이동물체와 배경에 홀이 발생하게 되고, 이 홀온 다른 프레임들의 정보를 이용하여 채움으로써 새로운 비디오를 생성한다. 입력 영상의 모든 프레임에 대해 각 물체의 중심을 추정하여 물체의 중심을 기준으로 시-공간 볼륨(spatio-temporal volume)을 생성하고, 복셀 매칭(voxel matching)을 통한 시간적 탐색(temporal search)을 수행한 후 두 물체를 분리한다. 가리는 물체 영역으로 판단된 부분을 삭제하고 공간적 탐색(spatial search) 방법을 이용하여 홀을 채워 가려짐이 있는 이동 물체 및 배경을 복원한다. 복원된 영상에서 블렌딩을 통해 솔기(seam)를 제거한다. 비디오카메라로 획득한 두 실영상을 이용하여 실험을 수행한 결과 가려진 물체를 복원한 새로운 비디오 영상을 생성할 수 있었다. Video Completion refers to a computer vision technique which restores damaged images by filling missing pixels with suitable color in a video sequence. We propose a new video completion technique to fill in image holes which are caused by removing an unnecessary object in a video sequence, where two objects cross each other in the presence of camera motion. We remove the closer object from a camera which results in image holes. Then these holes are filled by color information of some others frames. First of all, spatio-temporal volumes of occluding and occluded objects are created according to the centroid of the objects. Secondly, a temporal search technique by voxel matching separates and removes the occluding object. Finally. these holes are filled by using spatial search technique. Seams on the boundary of completed pixels we removed by a simple blending technique. Experimental results using real video sequences show that the proposed technique produces new completed videos.

Matching actions in presence of camera motion

When the camera viewing an action is moving, the motion observed in the video not only contains the motion of the actor but also the motion of the camera. At each time instant, in addition to the camera motion, a different view of the action is observed. In this paper, we propose a novel method to perform action recognition in presence of camera motion. Proposed method is based on the epipolar geometry between any two views. However, instead of relating two static views using the standard fundamental matrix, we model the motions of independently moving cameras in the equations governing the epipolar geometry and derive a new relation which is referred to as the fundamental matrix. Using the temporal fundamental matrix, a matching score between two actions is computed by evaluating the quality of the recovered geometry. We demonstrate the versatility of the proposed approach for action recognition in a number of challenging sequences.