SIFT 특징을 이용하여 중첩상황에 강인한 AAM 기반 얼굴 추적

A video tracking method based on spatial constrained coding (SCC) is proposed in this study. To characterise local image structure information, the dense scale-invariant feature transform (SIFT) descriptor is extracted for each pixel in the image. The proposed tracking method uses SCC model which adopts a new constrained strategy – weighted code, which is achieved by considering the sum of the weighted codes based on grey values of neighbouring pixels and distances between them. The proposed model is able to obtain robust code of corresponding pixels in the frames of complex scenes by taking spatial information into account, which enhances the stability of coding and makes the tracker more robust for object tracking. Twelve challenging sequences involving partial or full occlusion, large pose variation and drastic illumination change are chosen to test the proposed method. The experimental results show the proposed method performs excellent in comparison with other previously proposed trackers.

This paper presents a method for tracking of object movements and detecting of feature to identify video content using improved Scale-Invariant Feature Transform (SIFT). SIFT can robustly identify objects even among clutter and under partial occlusion, because the SIFT feature descriptor is invariant to uniform scaling, orientation, and also partially invariant to affine distortion and illumination changes. Even if the video drops frames or attacked, our method can extract the features. In our method we detect the video features from tracking the object's movement and make a dataset with feature sequences to identify video. In contrast to the existing tracking techniques, our method recognized reliable object coordinate. The developed algorithm will be an essential part of a completely tracking and identification system. To evaluate the performance of the proposed approach, we was experimenting with several genres of video. Compare with the original SIFT algorithm, we reducing up to 5 % in processing time was achieved for matching. Also appoint the position of the object area in tracking method make the proposed method automatic, fast and effective.

Cascade of descriptors to detect and track objects across any network of cameras

Manual creation of character animations using traditional tools is tedious and cumbersome for a novice animator. Video-to-image motion retargeting emerges as an automated approach for animating an input image using an exemplar video. State-of-the-art animation methods often produce artifacts in presence of drastic pose changes within a video. To address this issue, we propose LiveImage, which handles the large pose problem and overcomes various artifacts and shape distortions in the generated video frames. LiveImage uses a single-domain motion model with keypoint regularization first to produce coarse-grained frames that effectively capture motion and structural information. A motion condition network then estimates fine-grained video frames using denoising diffusion model to counteract unnatural artifacts and distortions arising from large pose changes. We perform comprehensive qualitative and quantitative evaluations, demonstrating its efficacy in overcoming challenges associated with motion transfer from video to image.

Geometric distortions resulting from large pose changes reduce the accuracy of motion measurements and interfere with the ability to generate artifact-free information. Our goal is to develop an algorithm and pulse sequence to enable motion-compensated, geometric distortion compensated diffusion-weighted MRI, and to evaluate its efficacy in correcting for the field inhomogeneity and position changes, induced by large and frequent head motions. Dual echo planar imaging (EPI) with a blip-reversed phase encoding distortion correction technique was evaluated in five volunteers in two separate experiments and compared with static field map distortion correction. In the first experiment, dual-echo EPI images were acquired in two head positions designed to induce a large field inhomogeneity change. A field map and a distortion-free structural image were acquired at each position to assess the ability of dual-echo EPI to generate reliable field maps and enable geometric distortion correction in both positions. In the second experiment, volunteers were asked to move to multiple random positions during a diffusion scan. Images were reconstructed using the dual-echo correction and a slice-to-volume registration (SVR) registration algorithm. The accuracy of SVR motion estimates was compared to externally measured ground truth motion parameters. Our results show that dual-echo EPI can produce slice-level field maps with comparable quality to field maps generated by the reference gold standard method. We also show that slice-level distortion correction improves the accuracy of SVR algorithms as slices acquired at different orientations have different levels of distortion, which can create errors in the registration process. Dual-echo acquisitions with blip-reversed phase encoding can be used to generate slice-level distortion-free images, which is critical for motion-robust slice to volume registration. The distortion corrected images not only result in better motion estimates, but they also enable a more accurate final diffusion image reconstruction.

We describe a novel RGBD relocalisation algorithm based on key point matching. It combines two components. First, a graph matching algorithm which takes into account the pairwise 3-D geometry amongst the key points, giving robust relocalisation. Second, a point selection process which provides an even distribution of the ‘most matchable’ points across the scene based on non-maximum suppression within voxels of a volumetric grid. This ensures a bounded set of matchable key points which enables tractable and scalable graph matching at frame rate. We present evaluations using a public dataset and our own more difficult dataset containing large pose changes, fast motion and non-stationary objects. It is shown that the method significantly out performs state-of-the-art methods.

In a cooperation task by multiple robots, it may happen that a working robot can not detect a target object for handling due to a sensor occlusion. In this situation, if another cooperative robot observes the working robot with the target object and detects their positions and orientations, it will be possible for the working robot to complete the handling task. Such behavior is a kind of indirect cooperation. This study proposes a method for such an indirect cooperation based on an observation by the partner robot. The observing robot obtains corresponding points of Scale-Invariant Feature Transformation (SIFT) on the working robot with hand and the target object from multiple captured images. The 3-D position of the target object and hand motion of the working robot can be detected by applying stereo vision theory to the points. The working robot is then able to get the relation between its hand and the target object indirectly from the observing robot. We describe each process to establish the indirect cooperation. Fundamental experiments confirmed the validity of presented method.

Photorealistic multi-view face synthesis from a single image is an important but challenging problem. Existing methods mainly learn a texture mapping model from the source face to the target face. However, they fail to consider the internal deformation caused by the change of poses, leading to the unsatisfactory synthesized results for large pose variations. In this paper, we propose a Gated Deformable Face Synthesis Network to model the deformation of faces that aids the synthesis of the target face image. Specifically, we propose a dual network that consists of two modules. The first module estimates the deformation of two views in the form of convolution offsets according to the input and target poses. The second one, on the other hand, leverages the predicted deformation offsets to create the target face image. In this way, pose changes are explicitly modeled in the face generator to cope with geometric transformation, by adaptively focusing on pertinent regions of the source image. To compensate offset estimation errors, we introduce a soft-gating mechanism that enables adaptive fusion between deformable features and primitive features. Extensive experimental results on five widely-used benchmarks show that our approach performs favorably against the state-of-the-arts on multi-view face synthesis, especially for large pose changes.

There are diverse approaches in face detection and recognition, highlighting algorithms, datasets, and practical applications. The Haar Cascade Classifier is a popular technique for fast and simple detection, though it is hindered by false positives and reduced accuracy in complex scenes. Advanced methods, such as combining machine learning algorithms with feature extraction techniques like Principal Component Analysis (PCA) and Three-Patch Local Binary Pattern (TPLBP), are examined for their higher recognition rates and improved accuracy. The use of datasets like ORL and Sheffield demonstrates robustness under various conditions, including changes in pose, lighting, and expression. Hybrid methods like Scale-Invariant Feature Transform (SIFT) and Principal Component Analysis integration, achieve remarkable accuracy on multiple datasets despite image variances. Notable contributions include the Dual Shot Face Detector algorithm for addressing challenges like scale variation and occlusion and the Viola-Jones algorithm, which is used for real-time detection with minimum computational overhead. The study also evaluates the performance of different algorithms across datasets and real-world applications, including automated attendance systems and emotion detection. This study conducts a comparative analysis of existing face detection methods, evaluating their accuracy, efficiency, and scalability across diverse environments. By identifying strengths and limitations, the study aims to provide insights and propose potential enhancements to guide the development of more robust and adaptable face detection solutions.

This paper proposes a method for classifying targets robust to geometric transformations of targets such as rotation, scale change, translation, and pose change. Targets which have rotation, scale change, and shift is firstly classified based on CM(Confidence Map) which is generated by similarity, scale ratio, and range of orientation for SIFT(Scale-Invariant Feature Transform) feature vectors. On the other hand, DB(DataBase) which is acquired in various angles is used to deal with pose variation of targets. Range of the angle is determined by comparing and analyzing the execution time and performance for sampling intervals. We experiment on various images which is geometrically changed to evaluate performance of proposed target classification method. Experimental results show that the proposed algorithm has a good classification performance.

This paper proposes human tracking and recognition method in a camera network. Human matching in a multi-camera surveillance system is a fundamental issue for increasing the accuracy of recognition in multiple views of cameras. In camera network, videos have different characteristics such as pose, scale and illumination. Therefore it is necessary to use a hybrid scheme of scale invariant feature transform to detection and recognition human's behaviors. The main focus of this paper is to analyze activities for tracking and recognition humans to extract trajectories. Extracting the trajectories help to detect abnormal behavior which may be occluded in single- camera surveillance. KEYWORDS: Camera network, Multi-camera surveillance, Human's behavior, Trajectories extraction. I. INTRODUCTION Tracking and behavior recognition are two fundamental tasks in video surveillance systems which are widely employed in commercial applications for purposes of statistics gathering and processing. The number of cameras and complexity of surveillance systems have been continuously increasing to have better coverage and accuracy. Multi-camera systems become increasingly attractive in machine vision. Applications include multi view object tracking, event detection, occlusion handling and etc. In this paper, we develop method for tracking and recognition by a traffic video surveillance system of two cameras with a partially overlapping field of view. This paper is organized as follows: an overview of the past works in section2. Our proposed architecture and algorithm is presented in section3. Results of subjective evaluations and objective performance measurements with respect to Ground-truth are presented in section4. Section5 contains the conclusion.

Maskrenderer: 3D-infused multi-mask realistic face reenactment

Although there exists dozens of vision based 3D head tracking methods, none of them considers the problem of large motion, especially the movement along the Z axis. In this paper we propose a novel tracking method to handle this problem by using Scale Invariant Feature Transform (SIFT) based registration algorithm. Salient SIFT features are first detected and tracked between two images, and then the 3D points corresponding to these features are obtained from a stereo camera. With these 3D points, a registration algorithm in a RANSAC framework is employed to detect the outliers and estimate the head pose. Performance evaluation shows an accurate pose recovery (3° RMS) when the head has large motion, even with movement along the Z axis was about 150 cm.

Long-term follow-up of transarterial balloon-assisted Onyx embolization for endovascular treatment of dural arteriovenous fistulas: A single-institution case series and literature review

Introduction/PurposeSince becoming available in 2007, flow diverters introduced the principle of endovascular reconstruction of the parent artery and exclusion of the aneurysm from the blood circulation, which has revolutionized intracranial...