Bohyung Han

Learning Deconvolution Network for Semantic Segmentation

We propose a novel semantic segmentation algorithm by learning a deep deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer net. The deconvolution network is composed of deconvolution and unpooling layers, which identify pixelwise class labels and predict segmentation masks. We apply the trained network to each proposal in an input image, and construct the final semantic segmentation map by combining the results from all proposals in a simple manner. The proposed algorithm mitigates the limitations of the existing methods based on fully convolutional networks by integrating deep deconvolution network and proposal-wise prediction, our segmentation method typically identifies detailed structures and handles objects in multiple scales naturally. Our network demonstrates outstanding performance in PASCAL VOC 2012 dataset, and we achieve the best accuracy (72.5%) among the methods trained without using Microsoft COCO dataset through ensemble with the fully convolutional network.

The Visual Object Tracking VOT2014 Challenge Results

Visual tracking has attracted a significant attention in the last few decades. The recent surge in the number of publications on tracking-related problems have made it almost impossible to follow the developments in the field. One of the reasons is that there is a lack of commonly accepted annotated data-sets and standardized evaluation protocols that would allow objective comparison of different tracking methods. To address this issue, the Visual Object Tracking (VOT) workshop was organized in conjunction with ICCV2013. Researchers from academia as well as industry were invited to participate in the first VOT2013 challenge which aimed at single-object visual trackers that do not apply pre-learned models of object appearance (model-free). Presented here is the VOT2013 benchmark dataset for evaluation of single-object visual trackers as well as the results obtained by the trackers competing in the challenge. In contrast to related attempts in tracker benchmarking, the dataset is labeled per-frame by visual attributes that indicate occlusion, illumination change, motion change, size change and camera motion, offering a more systematic comparison of the trackers. Furthermore, we have designed an automated system for performing and evaluating the experiments. We present the evaluation protocol of the VOT2013 challenge and the results of a comparison of 27 trackers on the benchmark dataset. The dataset, the evaluation tools and the tracker rankings are publicly available from the challenge website (http://votchallenge.net).

Learning Multi-domain Convolutional Neural Networks for Visual Tracking

We propose a novel visual tracking algorithm based on the representations from a discriminatively trained Convolutional Neural Network (CNN). Our algorithm pretrains a CNN using a large set of videos with tracking ground-truths to obtain a generic target representation. Our network is composed of shared layers and multiple branches of domain-specific layers, where domains correspond to individual training sequences and each branch is responsible for binary classification to identify target in each domain. We train each domain in the network iteratively to obtain generic target representations in the shared layers. When tracking a target in a new sequence, we construct a new network by combining the shared layers in the pretrained CNN with a new binary classification layer, which is updated online. Online tracking is performed by evaluating the candidate windows randomly sampled around the previous target state. The proposed algorithm illustrates outstanding performance in existing tracking benchmarks.

Sequential Kernel Density Approximation and Its Application to Real-Time Visual Tracking

Visual features are commonly modeled with probability density functions in computer vision problems, but current methods such as a mixture of Gaussians and kernel density estimation suffer from either the lack of flexibility by fixing or limiting the number of Gaussian components in the mixture or large memory requirement by maintaining a nonparametric representation of the density. These problems are aggravated in real-time computer vision applications since density functions are required to be updated as new data becomes available. We present a novel kernel density approximation technique based on the mean-shift mode finding algorithm and describe an efficient method to sequentially propagate the density modes over time. Although the proposed density representation is memory efficient, which is typical for mixture densities, it inherits the flexibility of nonparametric methods by allowing the number of components to be variable. The accuracy and compactness of the sequential kernel density approximation technique is illustrated by both simulations and experiments. Sequential kernel density approximation is applied to online target appearance modeling for visual tracking, and its performance is demonstrated on a variety of videos.

Robust routing in wireless ad hoc networks

A wireless ad hoc network is a collection of mobile nodes with no fixed infrastructure. The absence of a central authorization facility in dynamic and distributed environments requires collaboration among nodes. When a source searches for a route to a destination, an intermediate node can reply with its cached entry. To strengthen correctness of such a routing discovery process, we propose a method in which the intermediate node requests its next hop to send a confirmation message to the source. After receiving both a route reply and confirmation message, the source determines the validity of a path according to its policy. As a result, this strategy discourages malicious nodes from intercepting packets. Simulation results show a remarkable improvement in throughput (30% higher delivery ratio and 10% less data transmission overhead) with a moderate increase of control messages.

On-line density-based appearance modeling for object tracking

Object tracking is a challenging problem in real-time computer vision due to variations of lighting condition, pose, scale, and view-point over time. However, it is exceptionally difficult to model appearance with respect to all of those variations in advance; instead, on-line update algorithms are employed to adapt to these changes. We present a new on-line appearance modeling technique which is based on sequential density approximation. This technique provides accurate and compact representations using Gaussian mixtures, in which the number of Gaussians is automatically determined. This procedure is performed in linear time at each time step, which we prove by amortized analysis. Features for each pixel and rectangular region are modeled together by the proposed sequential density approximation algorithm, and the target model is updated in scale robustly. We show the performance of our method by simulations and tracking in natural videos

Image Question Answering Using Convolutional Neural Network with Dynamic Parameter Prediction

We tackle image question answering (ImageQA) problem by learning a convolutional neural network (CNN) with a dynamic parameter layer whose weights are determined adaptively based on questions. For the adaptive parameter prediction, we employ a separate parameter prediction network, which consists of gated recurrent unit (GRU) taking a question as its input and a fully-connected layer generating a set of candidate weights as its output. However, it is challenging to construct a parameter prediction network for a large number of parameters in the fully-connected dynamic parameter layer of the CNN. We reduce the complexity of this problem by incorporating a hashing technique, where the candidate weights given by the parameter prediction network are selected using a predefined hash function to determine individual weights in the dynamic parameter layer. The proposed network-joint network with the CNN for ImageQA and the parameter prediction network-is trained end-to-end through back-propagation, where its weights are initialized using a pre-trained CNN and GRU. The proposed algorithm illustrates the state-of-the-art performance on all available public ImageQA benchmarks.

Incremental density approximation and kernel-based Bayesian filtering for object tracking

Statistical density estimation techniques are used in many computer vision applications such as object tracking, background subtraction, motion estimation and segmentation. The particle filter (condensation) algorithm provides a general framework for estimating the probability density functions (pdf) of general non-linear and non-Gaussian systems. However, since this algorithm is based on a Monte Carlo approach, where the density is represented by a set of random samples, the number of samples is problematic, especially for high dimensional problems. In this paper, we propose an alternative to the classical particle filter in which the underlying pdf is represented with a semi-parametric method based on a mode finding algorithm using mean-shift. A mode propagation technique is designed for this new representation for tracking applications. A quasi-random sampling method in the measurement stage is used to improve performance, and sequential density approximation for the measurements distribution is performed for efficient computation. We apply our algorithm to a high dimensional color-based tracking problem, and demonstrate its performance by showing competitive results with other trackers.

Density-Based Multifeature Background Subtraction with Support Vector Machine

Background modeling and subtraction is a natural technique for object detection in videos captured by a static camera, and also a critical preprocessing step in various high-level computer vision applications. However, there have not been many studies concerning useful features and binary segmentation algorithms for this problem. We propose a pixelwise background modeling and subtraction technique using multiple features, where generative and discriminative techniques are combined for classification. In our algorithm, color, gradient, and Haar-like features are integrated to handle spatio-temporal variations for each pixel. A pixelwise generative background model is obtained for each feature efficiently and effectively by Kernel Density Approximation (KDA). Background subtraction is performed in a discriminative manner using a Support Vector Machine (SVM) over background likelihood vectors for a set of features. The proposed algorithm is robust to shadow, illumination changes, spatial variations of background. We compare the performance of the algorithm with other density-based methods using several different feature combinations and modeling techniques, both quantitatively and qualitatively.

Learning occlusion with likelihoods for visual tracking

We propose a novel algorithm to detect occlusion for visual tracking through learning with observation likelihoods. In our technique, target is divided into regular grid cells and the state of occlusion is determined for each cell using a classifier. Each cell in the target is associated with many small patches, and the patch likelihoods observed during tracking construct a feature vector, which is used for classification. Since the occlusion is learned with patch likelihoods instead of patches themselves, the classifier is universally applicable to any videos or objects for occlusion reasoning. Our occlusion detection algorithm has decent performance in accuracy, which is sufficient to improve tracking performance significantly. The proposed algorithm can be combined with many generic tracking methods, and we adopt L1 minimization tracker to test the performance of our framework. The advantage of our algorithm is supported by quantitative and qualitative evaluation, and successful tracking and occlusion reasoning results are illustrated in many challenging video sequences.