From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

A morphable model for the synthesis of 3D faces

There is a large variety of trackers, which have been proposed in the literature during the last two decades with some mixed success. Object tracking in realistic scenarios is a difficult problem, therefore, it remains a most active area of research in computer vision. A good tracker should perform well in a large number of videos involving illumination changes, occlusion, clutter, camera motion, low contrast, specularities, and at least six more aspects. However, the performance of proposed trackers have been evaluated typically on less than ten videos, or on the special purpose datasets. In this paper, we aim to evaluate trackers systematically and experimentally on 315 video fragments covering above aspects. We selected a set of nineteen trackers to include a wide variety of algorithms often cited in literature, supplemented with trackers appearing in 2010 and 2011 for which the code was publicly available. We demonstrate that trackers can be evaluated objectively by survival curves, Kaplan Meier statistics, and Grubs testing. We find that in the evaluation practice the F-score is as effective as the object tracking accuracy (OTA) score. The analysis under a large variety of circumstances provides objective insight into the strengths and weaknesses of trackers.

/pdf/visual-tracking-an-experimental-survey-50w2t40998.pdf

Visual Tracking: An Experimental Survey

Patterns of Attachment

Online Multi-Object Tracking (MOT) has wide applications in time-critical video analysis scenarios, such as robot navigation and autonomous driving. In tracking-by-detection, a major challenge of online MOT is how to robustly associate noisy object detections on a new video frame with previously tracked objects. In this work, we formulate the online MOT problem as decision making in Markov Decision Processes (MDPs), where the lifetime of an object is modeled with a MDP. Learning a similarity function for data association is equivalent to learning a policy for the MDP, and the policy learning is approached in a reinforcement learning fashion which benefits from both advantages of offline-learning and online-learning for data association. Moreover, our framework can naturally handle the birth/death and appearance/disappearance of targets by treating them as state transitions in the MDP while leveraging existing online single object tracking methods. We conduct experiments on the MOT Benchmark [24] to verify the effectiveness of our method.

/pdf/learning-to-track-online-multi-object-tracking-by-decision-we281ynssy.pdf

Learning to Track: Online Multi-object Tracking by Decision Making

Tracking generic human motion is highly challenging due to its high-dimensional state space and the various motion types involved. In order to deal with these challenges, a fusion formulation which integrates low- and high-dimensional tracking approaches into one framework is proposed. The low-dimensional approach successfully overcomes the high-dimensional problem of tracking the motions with available training data by learning motion models, but it only works with specific motion types. On the other hand, although the high-dimensional approach may recover the motions without learned models by sampling directly in the pose space, it lacks robustness and efficiency. Within the framework, the two parallel approaches, low- and high-dimensional, are fused via a probabilistic approach at each time step. This probabilistic fusion approach ensures that the overall performance of the system is improved by concentrating on the respective advantages of the two approaches and resolving their weak points. The experimental results, after qualitative and quantitative comparisons, demonstrate the effectiveness of the proposed approach in tracking generic human motion.

http://www.bmva.org/bmvc/2011/proceedings/paper57/abstract.pdf

Tracking Generic Human Motion via Fusion of Low- and High-Dimensional Approaches

Recently, fusion of low- and high-dimensional approaches shows its success in the generic human motion tracking. However, how to choose the trackers adaptively according to the motion types is still a challenging problem. This paper presents a trackers sampling approach for generic human motion tracking using both low- and high-dimensional trackers. Gaussian Process Dynamical Model(GPDM) is trained to learn the motion model of low-dimensional tracker, and it performs better on specific motion types. Annealed Particle Filtering(APF) shows its advantage in the tracking without limitation on motion types. We combine both of the two methods and automatically sample trackers according to the motion types that it is tracking on. To improve performance, trackers communication is adopt to keep the better state of trackers. The approach facilitates tracking of generic motions with low particle numbers.

Fusion of low-and high-dimensional approaches by trackers sampling for generic human motion tracking

/pdf/tracking-generic-human-motion-via-fusion-of-low-and-high-2lyg5vyl2y.pdf

Tracking Generic Human Motion via Fusion of Low- and High-Dimensional Approaches.

Successful multi-target tracking requires locating the targets and labeling their identities. This mission becomes significantly more challenging when many targets frequently interact with each other (present partial or complete occlusions). This paper presents an on-line supervised learning based method for tracking multiple interacting targets. When the targets do not interact with each other, multiple independent trackers are employed for training a classifier for each target. When the targets are in close proximity or present occlusions, the learned classifiers are used to assist in tracking. The tracking and learning supplement each other in the proposed method, which not only deals with tough problems encountered in multi-target tracking, but also ensures the entire process to be completely on-line. Various evaluations have demonstrated that this method performs better than previous methods when the interactions occur, and can maintain the correct tracking under various complex tracking situations, including crossovers, collisions and occlusions.

/pdf/vision-based-multiple-interacting-targets-tracking-via-on-extc4luj2z.pdf

Vision-Based Multiple Interacting Targets Tracking via On-Line Supervised Learning

Conventional deep learning based methods for object detection require a large amount of bounding box annotations for training, which is expensive to obtain such high quality annotated data. Few-shot object detection, which learns to adapt to novel classes with only a few annotated examples, is very challenging since the fine-grained feature of novel object can be easily overlooked with only a few data available. In this work, aiming to fully exploit features of annotated novel object and capture fine-grained features of query object, we propose Dense Relation Distillation with Context-aware Aggregation (DCNet) to tackle the few-shot detection problem. Built on the meta-learning based framework, Dense Relation Distillation module targets at fully exploiting support features, where support features and query feature are densely matched, covering all spatial locations in a feed-forward fashion. The abundant usage of the guidance information endows model the capability to handle common challenges such as appearance changes and occlusions. Moreover, to better capture scale-aware features, Context-aware Aggregation module adaptively harnesses features from different scales for a more comprehensive feature representation. Extensive experiments illustrate that our proposed approach achieves state-of-the-art results on PASCAL VOC and MS COCO datasets. Code will be made available at https://github.com/hzhupku/DCNet.

/pdf/dense-relation-distillation-with-context-aware-aggregation-2s7rgl0m1z.pdf

Jinshi Cui

Papers

Tracking Generic Human Motion via Fusion of Low- and High-Dimensional Approaches

Fusion of low-and high-dimensional approaches by trackers sampling for generic human motion tracking

Tracking Generic Human Motion via Fusion of Low- and High-Dimensional Approaches.

Vision-Based Multiple Interacting Targets Tracking via On-Line Supervised Learning

Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection