The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Multiple object tracking has been modelled as minimum cost network flow (MCNF) optimization problem recently. It is one of the most popular tracking-by-detection algorithm. MCNF is particularly effective due to its simple model and optimal solutions. However, complex scenarios, such as noisy detections and multi-objective interactions, make it difficult to track multi-objects in consecutive frames...
A new feature extraction method for early weak mechanical fault signal is proposed, which is based on the combination of double coupled Duffing oscillator (DCDO) and empirical mode decomposition (EMD). Firstly, machine fault signal is disintegrated into several intrinsic mode function (IMF) by EMD. After that, each intrinsic mode function which contains fault characteristics is inputted to the DCDO...
We propose an offline method to match tracked objects from two sensors in complex and real life traffic scenarios, which can be used to build an automatic system for offline sensor verification of advanced driver assistance systems and autonomous driving. Detected objects in each of the sensors are described by a dynamic state vector representing their position, speed, and the physical shape of the...
Behavior analysis of vehicles surrounding the egovehicle is an essential component in safe and pleasant autonomous driving. This study develops a framework for activity classification of observed on-road vehicles using 3D trajectory cues and a Long Short Term Memory (LSTM) model. As a case study, we aim to classify maneuvers of surrounding vehicles at four way intersections. LIDAR, GPS, and IMU measurements...
Phase synchronization issue, that is caused by spotting gestures from video stream, varying frame-rates, speed of subject's implementation, should be overcome in developing Human-Computer Interaction (HCI) application using dynamic hand gestures. This paper tackles an interpolation technique to efficiently solve this issue. We firstly propose a new representation of dynamic hand gestures space that...
The Highly Automated Driving Map (HAD Map), is an essential and significant research topic in automated driving. In the meanwhile, the corrugated beam guardrail, known as one kind of the traffic crash barrier, is one of the most important elements in the HAD Map. Our novel contribution in this paper is proposing a method to detect corrugated beam guardrail automatically from mobile laser scanning...
In this paper we propose a novel technique for detecting loop closures on a trajectory by matching sequences of images instead of single instances. We build upon well established techniques for creating a bag of visual words with a tree structure and we introduce a significant novelty by extending these notions to describe the visual information of entire regions using Visual-Word-Vectors. The fact...
The availability of commodity multi-camera systems such as Google Jump, Jaunt, and Lytro Immerge have brought new demand for reliable and efficient extrinsic camera calibration. State-of-the-art solutions generally require that adjacent, if not all, cameras observe a common area or employ known scene structures. In this paper, we present a novel multi-camera calibration technique that eliminates such...
For recognizing human actions in video sequences, it is necessary to extract sufficient information which can represent motion features. In recent years, dense trajectories based action recognition algorithms attract more attention for containing rich spatio-temporal information. However, these algorithms are always faced with cluttered background. To solve this problem, we involve object tracking...
As an automatic tracking system, the shipboard Automatic Identification System (AIS) has been widely adopted to identify and locate the vessels by electronically exchanging data with other nearby ships. With the development of computer technology, AIS-based visualization of vessel traffic has attracted increasing attention during the past several years. The vessel density visualization can be used...
In recent years, location-based services and indoor positioning systems gained increasing importance for both, research and industry. Visual localization systems have the advantage of not being dependent on dedicated infrastructure and thus are especially interesting for navigation within buildings. While there are already approaches of using pre-recorded databases of reference images to obtain an...
For real-time feedback and cost-efficient analysis from sport videos, it is essential to automatically identify players. In this paper, we propose a method for identifying sport players in videos. Our method uses wearable sensors to obtain their motions. Player identification is achieved by motion feature matching between (unknown) players in videos and wearable sensors whose IDs are already known...
Recently, Simultaneous Localization And Mapping (SLAM) has been getting more and more popular on the applications of mobile robot and unmanned aerial vehicles. If combined with semi-dense mapping, monocular SLAM will have a good prospect for multi-applications such as visual navigation. In addition, robust tracking is a pivotal role in complex and volatile situation and also it determines the quality...
In this paper, we address a problem of precise online localization of a hexapod walking robot operating in rough terrains. We consider an existing Simultaneous Localization and Mapping approach with a low cost structured light (RGB-D) sensor. We propose to combine this sensor and localization method with the developed adaptive motion gait that allows the robot to crawl various types of terrain, such...
Depth image based human action recognition has attracted many attentions due to the popularity of the depth sensors. However, accurate recognition still remains a challenge because of various object appearances, poses and video sequences. In this paper, a novel skeleton joints descriptor based on 3D Moving Trend and Geometry (3DMTG) property is proposed for human action recognition. Specifically,...
As closed circuit television which had been used only for surveillance or identification has developed rapidly the research on intelligent surveillance systems is getting increased interest. Above all, abnormal event detection is becoming an essential part of surveillance systems by detecting or identifying actions or situations which are not commonly occurred in general. In this work, we propose...
This paper provides an efficient framework for recognizing human interactions based on deep learning based architecture. The Harris corner points and the histogram form the feature vector of the spatiotemporal volume. The feature vector extraction is restricted to the region of interaction. A stacked autoencoder configuration is embedded in the deep learning framework used for classification. The...
Currently, the understanding of the human mobility is an important challenge that has a large number of applications, especially in the study of a nation's ability to thrive economically and socially. Some works have shown that, it is possible to observe developed and developing countries reviewing their administrative regions borders, in order to reduce costs, or to solve ethnic claims and/or independence...
Action classification in videos has been a very active field of research over the past years. Human action classification is a research field with application to various areas such as video indexing, surveillance, human-computer interfaces, among others. In this paper, we propose a strategy based on decreasing the number of features in order to improve accuracy in the human action classification task...
We propose a new methodology to detect social aspects of crowds in video sequences based on pedestrian features, which are obtained through image processing/computer vision techniques. The main idea is to apply and extend the concepts of Fundamental Diagram (FD) with more features, such as grouping and collectivity. Using crowd features we identify the crowd type and the main characteristics. In addition,...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.