Irregular Camera Research Articles

Optimal Camera Placement to Generate 3D Reconstruction of a Mixed-Reality Human in Real Environments

Virtual reality and augmented reality are increasingly used for immersive engagement by utilizing information from real environments. In particular, three-dimensional model data, which is the basis for creating virtual places, can be manually developed using commercial modeling toolkits, but with the advancement of sensing technology, computer vision technology can also be used to create virtual environments. Specifically, a 3D reconstruction approach can generate a single 3D model from image information obtained from various scenes in real environments using several cameras (multi-cameras). The goal is to generate a 3D model with excellent precision. However, the rules for choosing the optimal number of cameras and settings to capture information from in real environments (e.g., actual people) employing several cameras in unconventional positions are lacking. In this study, we propose an optimal camera placement strategy for acquiring high-quality 3D data using an irregular camera placement, essential for organizing image information while acquiring human data in a three-dimensional real space, using multiple irregular cameras in real environments. Our results show that installation costs can be lowered by arranging a minimum number of multi-camera cameras in an arbitrary space, and automated virtual human manufacturing with high accuracy can be conducted using optimal irregular camera location.

Online real-time pedestrian tracking from medium altitude aerial footage with camera motion cancellation

Using medium altitude footage in various image based pedestrian detection and tracking tasks have several advantages as opposed to low altitude footage. For instance, much larger covered area, or weaker perspective distortions and occlusions. Furthermore, it does not pose privacy issues. However, it also has a disadvantage that is the irregular camera motion. Such motions can be observed with some ground level footage as well. Some state-of-the-art multi-object tracking (MOT) algorithms, which excel at pedestrian tracking, handle these implicitly, however this is insufficient in the case of medium altitude footage. The problem is further enhanced in online real-time tracking where frames may need to be skipped. Although there are explicit frame registration methods developed for wide area motion imagery (WAMI), they operate on assumptions that are not true in medium altitude footage such as the background is mostly stationary. We show that by augmenting the pedestrian tracking algorithms with a simple visual object tracking (VOT) based frame registration method their accuracy on medium altitude footage can be substantially improved without hindering the execution speed. Moreover, we show that the algorithms’ execution speed can be significantly increased by better utilization of the resources. To evaluate these, we introduce helicopter video sequences with MOT annotation.

Single Modality-Based Event Detection Framework for Complex Videos

Event detection of rare and complex events in large video datasets or in unconstrained user-uploaded videos on internet is a challenging task. The presence of irregular camera movement, viewpoint changes, illumination variations and significant changes in the background make extremely difficult to capture underlying motion in videos. In addition, extraction of features using different modalities (single streams) may offer computational complexities and cause abstraction of confusing and irrelevant spatial and semantic features. To address this problem, we present a single stream (RGB only) based on feature of spatial and semantic features extracted by modified 3D Residual Convulsion Network. We combine the spatial and semantic features based on this assumption that difference between both types of features can discover the accurate and relevant features. Moreover, introduction of temporal encoding builds the relationship in consecutive video frames to explore discriminative long-term motion patterns. We conduct extensive experiments on prominent publically available datasets. The obtained results demonstrate the great power of our proposed model and improved accuracy compared with existing state-of-the-art methods.

일반화 대칭 변환 기반의 웨이퍼 위치 인식

본 논문에서는 카메라를 이용한 웨이퍼 위치 인식 알고리즘을 제안한다. 먼저 챔버 외부의 조명 반사와 카메라로 인한 영상의 원근 왜곡을 제거하기 위하여 투영 변환을 적용하여 실제 웨이퍼와 같이 정원의 형태로 복원한다. 다음, 에지 검출 알고리즘을 이용하여 웨이퍼의 외부 경계를 추출한 후, 일반화 대칭 변환을 적용하여 원을 검출함으로서 웨이퍼의 위치를 검사한다. 일반화 대칭 변환은 영상에서 화소쌍들 사이의 대칭값을 거리 가중치 함수, 위상 가중치 함수, 화소들의 기울기 크기와 로그 맵핑이 결합되어 영상에서 관심 영역을 추출한다. 제안하는 방법을 적용하여 웨이퍼가 올바른 위치에 장착되었는가를 검사하여 클리닝 시스템 장비와 웨이퍼의 파손을 미연에 방지한다. This paper proposes the wafer position recognition algorithm using camera. First, for eliminating the image distortions caused by the illumination and the irregular camera position, the wafer image is restored as a circle through projective transformation. Next, we use edge detection algorithm to extract the wafer's edge and then apply Generalized Symmetry Transform(GST) to extract a circle. The GST evaluates symmetry between two points by combining a distance weight function, a phase weight function, and a logarithmic mapping of the points' intensities and detecting interest regions. Trough several experiments, we found out the proposed method is able to prevent the cleaning system and the wafer from damaging.

Optimizing inter-view prediction structures for multi-view video coding using simulated annealing

New video applications, such as 3D video and free viewpoint video, require efficient compression of multi-view video. In addition to temporal redundancy, exploiting the inter-view redundancy is crucial to improve the performance of multi-view video coding. In this paper, we present a novel method to construct the optimal inter-view prediction structure for multi-view video coding using simulated annealing. In the proposed model, the design of the prediction structure is converted to the arrangement of coding order. Then, a simulated annealing algorithm is employed to minimize the total cost for obtaining the best coding order. This method is applicable to arbitrary irregular camera arrangements. As experiment results reveal, the annealing process converges to satisfactory results rapidly and the generated optimal prediction structure outperforms the reference prediction structure of the joint multi-view video model (JMVM) by 0.1–0.8 dB PSNR gains.

Detecting irregular camera events in time-multiplexed videos

Novel robust statistical methods for detecting irregular camera events in time-multiplexed video streams are presented. Hidden Markov and hidden semi-Markov model based real-time detectors have been developed for video segmentation and anomalous event detection. The performance of the detectors has been demonstrated with real-life outdoor videos recorded by low-quality cameras.