Finding Pareto-optimal solutions is a basic approach in multi-objective combinatorial optimization. In this paper, we focus on the 0-1 multi-objective knapsack problem, and present an algorithm to enumerate all its Pareto-optimal solutions, which improves upon the method proposed by Bazgan et al. Our algorithm is based on dynamic programming techniques using an efficient data structure called zero-suppressed binary decision diagram (ZDD), which handles a set of combinations compactly. In our algorithm, we utilize ZDDs for storing all the feasible solutions compactly, and pruning inessential partial solutions as quickly as possible. As an output of the algorithm, we can obtain a useful ZDD indexing all the Pareto-optimal solutions. The results of our experiments show that our algorithm is faster than the previous method for various types of three- and four-objective instances, which are difficult problems to solve.

Visual object detection on embedded systems involves a multi-objective optimization problem in the presence of trade-offs between power consumption, processing performance, and detection accuracy. For a new Pareto solution with high processing performance and low power consumption, this paper proposes a hardware architecture for decision tree ensemble using multiple channels of features. For efficient detection, the proposed architecture utilizes the dimensionality of feature channels in addition to parallelism in image space and adopts task scheduling to attain random memory access without conflict. Evaluation results show that an FPGA implementation of the proposed architecture with an aggregated channel features pedestrian detector can process 229 million samples per second at 100MHz operation frequency while it requires a relatively small amount of resources. Consequently, the proposed architecture achieves 350fps processing performance for 1080P Full HD images and outperforms conventional object detection hardware architectures developed for embedded systems.

Behaviors of an object-oriented system can be visualized as reverse-engineered sequence diagrams from execution traces. This approach is a valuable tool for program comprehension tasks. However, owing to the massiveness of information contained in an execution trace, a reverse-engineered sequence diagram is often afflicted by a scalability issue. To address this issue, many trace summarization techniques have been proposed. Most of the previous techniques focused on reducing the vertical size of the diagram. To cope with the scalability issue, decreasing the horizontal size of the diagram is also very important. Nonetheless, few studies have addressed this point; thus, there is a lot of needs for further development of horizontal summarization techniques. We present in this paper a method for identifying core objects for trace summarization by analyzing reference relations and dynamic properties. Visualizing only interactions related to core objects, we can obtain a horizontally compactified reverse-engineered sequence diagram that contains system's key behaviors. To identify core objects, first, we detect and eliminate temporary objects that are trivial for a system by analyzing reference relations and lifetimes of objects. Then, estimating the importance of each non-trivial object based on their dynamic properties, we identify highly important ones (i.e., core objects). We implemented our technique in our tool and evaluated it by using traces from various open-source software systems. The results showed that our technique was much more effective in terms of the horizontal reduction of a reverse-engineered sequence diagram, compared with the state-of-the-art trace summarization technique. The horizontal compression ratio of our technique was 134.6 on average, whereas that of the state-of-the-art technique was 11.5. The runtime overhead imposed by our technique was 167.6% on average. This overhead is relatively small compared with recent scalable dynamic analysis techniques, which shows the practicality of our technique. Overall, our technique can achieve a significant reduction of the horizontal size of a reverse-engineered sequence diagram with a small overhead and is expected to be a valuable tool for program comprehension.

Advanced metering infrastructure (AMI) is a kind of wireless sensor network that provides two-way communication between smart meters and city utilities in the neighborhood area of the smart grid. And the routing protocol for low-power and lossy network (RPL) is being considered for use in AMI networks. However, there still exist several problems that need to be solved, especially with respect to QoS guarantees. To address these problems, an improved algorithm of RPL based on triangle module operator named as TMO is proposed. TMO comprehensively evaluates routing metrics: end-to-end delay, number of hops, expected transmission count, node remaining energy, and child node count. Moreover, TMO uses triangle module operator to fuse membership functions of these routing metrics. Then, the node with minimum rank value will be selected as preferred parent (the next hop). Consequently, the QoS of RPL-based AMI networks can be guaranteed effectively. Simulation results show that TMO offers a great improvement over several the most popular schemes for RPL like ETXOF, OF-FL and additive composition metric manners in terms of network lifetime, average end-to-end delay, average packet loss ratio, average hop count from nodes to root, etc.

A lot of vision systems have been embedded in devices around us, like mobile phones, vehicles and UAVs. Many of them still need interactive operations of human users. However, specifying accurate object information could be a challenging task due to video jitters caused by camera shakes and target motions. In this paper, we first collect practical hand drawn bounding boxes on real-life videos which are captured by hand-held cameras and UAV-based cameras. We give a deep look into human-computer interactive operations on unstable images. The collected data shows that human input suffers heavy deviations which are harmful to interaction accuracy. To achieve robust interactions on unstable platforms, we propose a target-focused video stabilization method which utilizes a proposal-based object detector and a tracking-based motion estimation component. This method starts with a single manual click and outputs stabilized video stream in which the specified target stays almost stationary. Our method removes not only camera jitters but also target motions simultaneously, therefore offering an comfortable environment for users to do further interactive operations. The experiments demonstrate that the proposed method effectively eliminates image vibrations and significantly increases human input accuracy.

Extracting 3D information from a single image is an interesting but ill-posed problem. Especially for those artificial objects with less texture such as smooth metal devices, the decrease of object detail makes the problem more challenging. Aiming at the texture-less object with symmetric structure, this paper proposes a novel method for 3D pose estimation from a single image by introducing implicit structural symmetry and context constraint as priori-knowledge. Firstly, by parameterized representation, the texture-less object is decomposed into a series of sub-objects with regular geometric primitives. Accordingly, the problem of 3D pose estimation is converted to a parameter estimation problem, which is implemented by primitive fitting algorithm. Then, the context prior among sub-objects is introduced for parameter refinement via the augmentedLagrange optimization. The effectiveness of the proposed method is verified by the experiments based on simulated and measured data.

In this paper, we propose a method of salient object detection based on distributed seeds and a co-propagation of seed information. Salient object detection is a technique which estimates important objects for human by calculating saliency values of pixels. Previous salient object detection methods often produce incorrect saliency values near salient objects in the case of images which have some objects, called the leakage of saliencies. Therefore, a method based on a co-propagation, the scale invariant feature transform, the high dimensional color transform, and machine learning is proposed to reduce the leakage. Firstly, the proposed method estimates regions clearly located in salient objects and the background, which are called as seeds and resultant seeds, are distributed over images. Next, the saliency information of seeds is simultaneously propagated, which is then referred as a co-propagation. The proposed method can reduce the leakage caused because of the above methods when the co-propagation of each information collide with each other near the boundary. Experiments show that the proposed method significantly outperforms the state-of-the-art methods in mean absolute error and F-measure, which perceptually reduces the leakage.

Most people are concerned about their appearance, and the easiest way to change the appearance is to change the hairstyle. However, except for professional hairstylists, it is difficult to objectively judge which hairstyle suits them. Currently, oval faces are generally said to be the ideal facial shape in terms of suitability to various hairstyles. Meanwhile, field of visual perception (FVP), proposed recently in the field of cognitive science, has attracted attention as a model to represent the visual perception phenomenon. Moreover, a computation model for digital images has been proposed, and it is expected to be used in quantitative evaluation of sensibility and sensitivity called “kansei.” Quantitative evaluation of “goodness of patterns” and “strength of impressions” by evaluating distributions of the field has been reported. However, it is unknown whether the evaluation method can be generalized for use in various subjects, because it has been applied only to some research subjects, such as characters, text, and simple graphics. In this study, for the first time, we apply FVP to facial images with various hairstyles and verify whether it has the potential of evaluating impressions of female faces. Specifically, we verify whether the impressions of facial images that combine various facial shapes and female hairstyles can be represented using FVP. We prepare many combinational images of facial shapes and hairstyles and conduct a psychological experiment to evaluate their impressions. Moreover, we compute the FVP of each image and propose a novel evaluation method by analyzing the distributions. The conventional and proposed evaluation values correlated to the psychological evaluation values after normalization, and demonstrated the effectiveness of the FVP as an image feature quantity to evaluate faces.

Motivated by the observation that certain convolutional channels of a Convolutional Neural Network (CNN) exhibit object specific responses, we seek to discover and exploit the convolutional channels of a CNN in which neurons are activated by the presence of specific objects in the input image. A method for explicitly fine-tuning a pre-trained CNN to induce object specific channel (OSC) and systematically identifying it for the human faces has been developed. In this paper, we introduce a multi-scale approach to constructing robust face heatmaps based on OSC features for rapidly filtering out non-face regions thus significantly improving search efficiency for face detection. We show that multi-scale OSC can be used to develop simple and compact face detectors in unconstrained settings with state of the art performance.

We propose a novel object recognition system that is able to (i) work in real-time while reconstructing segmented 3D maps and simultaneously recognize objects in a scene, (ii) manage various kinds of objects, including those with smooth surfaces and those with a large number of categories, utilizing a CNN for feature extraction, and (iii) maintain high accuracy no matter how the camera moves by distributing the viewpoints for each object uniformly and aggregating recognition results from each distributed viewpoint as the same weight. Through experiments, the advantages of our system with respect to current state-of-the-art object recognition approaches are demonstrated on the UW RGB-D Dataset and Scenes and on our own scenes prepared to verify the effectiveness of the Viewpoint-Class-based approach.

Tracking-by-detection methods consider tracking task as a continuous detection problem applied over video frames. Modern tracking-by-detection trackers have online learning ability; the update stage is essential because it determines how to modify the classifier inherent in a tracker. However, most trackers search for the target within a fixed region centered at the previous object position; thus, they lack spatiotemporal consistency. This becomes a problem when the tracker detects an incorrect object during short-term occlusion. In addition, the scale of the bounding box that contains the target object is usually assumed not to change. This assumption is unrealistic for long-term tracking, where the scale of the target varies as the distance between the target and the camera changes. The accumulation of errors resulting from these shortcomings results in the drift problem, i.e. drifting away from the target object. To resolve this problem, we present a drift-free, online learning-based tracking-by-detection method using a single static camera. We improve the latent structured support vector machine (SVM) tracker by designing a more robust tracker update step by incorporating two Kalman filter modules: the first is used to predict an adaptive search region in consideration of the object motion; the second is used to adjust the scale of the bounding box by accounting for the background model. We propose a hierarchical search strategy that combines Bhattacharyya coefficient similarity analysis and Kalman predictors. This strategy facilitates overcoming occlusion and increases tracking efficiency. We evaluate this work using publicly available videos thoroughly. Experimental results show that the proposed method outperforms the state-of-the-art trackers.

We propose a framework to detect lug position and orientation in robotics that is insensitive to the lug orientation, incorporating a proposed optimization based on the artificial bee colony genetic algorithm. Experimental results show that the proposed optimization method outperformed traditional artificial bee colony and other meta-heuristics in the considered cases and was up to 3 times faster than the traditional approach. The proposed detection framework provided excellent performance to detect lug objects for all test cases.

360 videos have recently become a popular virtual reality content type. However, a good quality metric for 360 videos is still an open issue. In this work, our goal is to identify appropriate objective quality metrics for 360 video communications. Especially, fourteen objective quality measures at different processing phases are considered. Also, a subjective test is conducted in this study. The relationship between objective quality and subjective quality is investigated. It is found that most of the PSNR-related quality measures are well correlated with subjective quality. However, for evaluating video quality across different contents, a content-based quality metric is needed.

Object detection has been a hot topic of image processing, computer vision and pattern recognition. In recent years, training a model from labeled images using machine learning technique becomes popular. However, the relationship between training samples is usually ignored by existing approaches. To address this problem, a novel approach is proposed, which trains Siamese convolutional neural network on feature pairs and finely tunes the network driven by a small amount of training samples. Since the proposed method considers not only the discriminative information between objects and background, but also the relationship between intraclass features, it outperforms the state-of-arts on real images.

Object detection is an essential and expensive process in many computer vision systems. Standard off-the-shelf embedded processors are hard to achieve performance-power balance for implementation of object detection applications. In this work, we explore an Application Specific Instruction set Processor (ASIP) for object detection using Histogram of Oriented Gradients (HOG) feature. Algorithm simplifications are adopted to reduce memory bandwidth requirements and mathematical complexity without losing reliability. Also, parallel histogram generation and on-the-fly Support Vector Machine (SVM) calculation architecture are employed to reduce the necessary cycle counts. The HOG algorithm on the proposed ASIP was accelerated by a factor of 63x compared to the pure software implementation. The ASIP was synthesized for a standard 90nm CMOS library, with a silicon area of 1.31mm2 and 47.8mW power consumption at a 200MHz frequency. Our object detection processor can achieve 42 frames-per-second (fps) on VGA video. The evaluation and implementation results show that the proposed ASIP is both area-efficient and power-efficient while being competitive with commercial CPUs/DSPs. Furthermore, our ASIP exhibits comparable performance even with hard-wire designs.

Many real world optimization problems involving sets of agents can be modeled as Distributed Constraint Optimization Problems (DCOPs). A DCOP is defined as a set of variables taking values from finite domains, and a set of constraints that yield costs based on the variables' values. Agents are in charge of the variables and must communicate to find a solution minimizing the sum of costs over all constraints. Many applications of DCOPs include multiple criteria. For example, mobile sensor networks must optimize the quality of the measurements and the quality of communication between the agents. This introduces trade-offs between solutions that are compared using the concept of Pareto dominance. Multi-Objective Distributed Constraint Optimization Problems (MO-DCOPs) are used to model such problems where the goal is to find the set of Pareto optimal solutions. This set being exponential in the number of variables, it is important to consider fast approximation algorithms for MO-DCOPs. The bounded multi-objective max-sum (B-MOMS) algorithm is the first and only existing approximation algorithm for MO-DCOPs and is suited for solving a less-constrained problem. In this paper, we propose a novel approximation MO-DCOP algorithm called Distributed Pareto Local Search (DPLS) that uses a local search approach to find an approximation of the set of Pareto optimal solutions. DPLS provides a distributed version of an existing centralized algorithm by complying with the communication limitations and the privacy concerns of multi-agent systems. Experiments on a multi-objective extension of the graph-coloring problem show that DPLS finds significantly better solutions than B-MOMS for problems with medium to high constraint density while requiring a similar runtime.

In this letter, we propose a robust and fast tracking framework by combining local and global appearance models to cope with partial occlusion and pose variations. The global appearance model is represented by a correlation filter to efficiently estimate the movement of the target and the local appearance model is represented by local feature points to handle partial occlusion and scale variations. Then global and local appearance models are unified via the Bayesian inference in our tracking framework. We experimentally demonstrate the effectiveness of the proposed method in both terms of accuracy and time complexity, which takes 12ms per frame on average for benchmark datasets.

Recently, numerous methods have been proposed to tackle the problem of fine-grained image classification. However, rare of them focus on the pre-processing step of image alignment. In this paper, we propose a new pre-processing method with the aim of reducing the variance of objects among the same class. As a result, the variance of objects between different classes will be more significant. The proposed approach consists of four procedures. The “parts” of the objects are firstly located. After that, the rotation angle and the bounding box could be obtained based on the spatial relationship of the “parts”. Finally, all the images are resized to similar sizes. The objects in the images possess the properties of translation, scale and rotation invariance after processed by the proposed method. Experiments on the CUB-200-2011 and CUB-200-2010 datasets have demonstrated that the proposed method could boost the recognition performance by serving as a pre-processing step of several popular classification algorithms.

In this study, we address the problem of online RGB-D tracking which confronted with various challenges caused by deformation, occlusion, background clutter, and abrupt motion. Various trackers have different strengths and weaknesses, and thus a single tracker can merely perform well in specific scenarios. We propose a 3D tracker-level fusion algorithm (TLF3D) which enhances the strengths of different trackers and suppresses their weaknesses to achieve robust tracking performance in various scenarios. The fusion result is generated from outputs of base trackers by optimizing an energy function considering both the 3D cube attraction and 3D trajectory smoothness. In addition, three complementary base RGB-D trackers with intrinsically different tracking components are proposed for the fusion algorithm. We perform extensive experiments on a large-scale RGB-D benchmark dataset. The evaluation results demonstrate the effectiveness of the proposed fusion algorithm and the superior performance of the proposed TLF3D tracker against state-of-the-art RGB-D trackers.

Feature extractor is an important component of a tracker and the convolutional neural networks (CNNs) have demonstrated excellent performance in visual tracking. However, the CNN features cannot perform well under conditions of low illumination. To address this issue, we propose a novel deep correlation tracker with backtracking, which consists of target translation, backtracking and scale estimation. We employ four correlation filters, one with a histogram of oriented gradient (HOG) descriptor and the other three with the CNN features to estimate the translation. In particular, we propose a backtracking algorithm to reconfirm the translation location. Comprehensive experiments are performed on a large-scale challenging benchmark dataset. And the results show that the proposed algorithm outperforms state-of-the-art methods in accuracy and robustness.