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.
In this paper, a unified deep convolutional architecture is proposed to address the problems in the person re-identification task. The proposed method adaptively learns the discriminative deep mid-level features of a person and constructs the correspondence features between an image pair in a data-driven manner. The previous Siamese structure deep learning approaches focus only on pair-wise matching...
Plasma arc cutting is a complex process with substantial interaction between process parameters. These manifest in deviations in the properties of the cut such as kerf width and kerf angle. Developing relationships between process parameters and aspects of the cut requires a large amount of data. This paper presents a novel method that applies computer vision to assess the kerf width against plasma...
Up to the present day, GPS signals are the key component in almost all outdoor navigation tasks of robotic platforms. To obtain the platform pose, comprising the position as well as the orientation, and receive information at a higher frequency, the GPS signals are commonly used in a GPS-corrected inertial navigation system (INS). The GPS is a critical single point of failure, especially for autonomous...
Lane estimation plays a central role for Driver Assistance Systems, therefore many approaches have been proposed to measure its performance. However, no commonly agreed metric exists. In this work, we first present a detailed survey of the current measures. Most of them apply pixel-level benchmarks on camera images and require a time-consuming and fault-prone labeling process. Moreover, these metrics...
This paper describes the implementation of a 3D handheld scanning approach based on Kinect. User may get the 3D scans at a very fast rate using real time scanning devices like Kinect. These devices have been utilized in several applications, but the scanning lacks in the accuracy and reliability of the 3D data, which makes their employment a difficult task. This research proposed the 3D handheld scanning...
In this work, several state-of-the-art Blind Image Quality Assessment (IQA) metrics and measures are evaluated in order to verify how they behave on extreme conditions such as the ones found on pictures of metallic surfaces. This is an important research topic given that the automation of the image acquisition comprehends one of the essential steps towards the automation and autonomy in many fields...
This paper presents a fusion of monocular camera-based metric localization, IMU and odometry in dynamic environments of public roads. We build multiple vision-based maps and use them at the same time in localization phase. For the mapping phase, visual maps are built by employing ORB-SLAM and accurate metric positioning from LiDAR-based NDT scan matching. This external positioning is utilized to correct...
In recent years, remarkable breakthrough has been achieved in person re-identification (Re-ID). However most methods are only tested in the closed-world setting where the probe person is assumed to be one of the gallery people. In this paper, we tackle a more realistic problem, open-world Re-ID, which requires to find out whether the probe person is among the gallery or not, and if so, who he is....
Person re-identification is an important task in video surveillance systems. It can be formally defined as establishing the correspondence between images of a person taken from different cameras at different times. In this paper, we present a two stream convolutional neural network where each stream is a Siamese network. This architecture can learn spatial and temporal information separately. We also...
The intensive annotation cost and the rich but unlabeled data contained in videos motivate us to propose an unsupervised video-based person re-identification (re-ID) method. We start from two assumptions: 1) different video tracklets typically contain different persons, given that the tracklets are taken at distinct places or with long intervals; 2) within each tracklet, the frames are mostly of the...
While metric learning is important for Person reidentification (RE-ID), a significant problem in visual surveillance for cross-view pedestrian matching, existing metric models for RE-ID are mostly based on supervised learning that requires quantities of labeled samples in all pairs of camera views for training. However, this limits their scalabilities to realistic applications, in which a large amount...
Direct method for visual odometry has gained popularity, it needs not to compute feature descriptor and uses the actual values of camera sensors directly. Hence, it is very fast. However, its accuracy and consistency are not satisfactory. Based on these considerations, we propose a tightly-coupled, optimization-based method to fuse inertial measurement unit (IMU) and visual measurement, in which uses...
Mobile phones equipped with a monocular camera and an inertial measurement unit (IMU) are ideal platforms for augmented reality (AR) applications, but the lack of direct metric distance measurement and the existence of aggressive motions pose significant challenges on the localization of the AR device. In this work, we propose a tightly-coupled, optimization-based, monocular visual-inertial state...
This paper proposes a scheme for observing cooperative Unmanned Surface Vehicles (USV), using a rotorcraft Unmanned Aerial Vehicle (UAV) with camera movements (tilt and yaw) prioritized over UAV movements. Most of the current researches consider a fixed-wing type UAV for surveillance of multiple moving targets (MMT), whose functionality is limited to just UAV movements. Experiments in simulation are...
Camera-enabled sensors deployed for visual monitoring will cover a region of the target field, providing information for many innovative applications based on wireless sensing. Actually, some areas of the monitored field may have more relevance than others, according to the characteristics of the applications, which may indicate that such areas need better coverage to avoid blind spots and achieve...
This work presents a video-based sequence synchronization algorithm to be used in real-time video surveillance applications. The signals are aligned based on an online dynamic time warping approach that uses only video content information. The algorithm was tested in the alignment of reference and target videos acquired in a cluttered industrial environment with a moving camera. During each recording,...
Person Re-Identification (person re-id) is a crucial task as its applications in visual surveillance and human-computer interaction. In this work, we present a novel joint Spatial and Temporal Attention Pooling Network (ASTPN) for video-based person re-identification, which enables the feature extractor to be aware of the current input video sequences, in a way that interdependency from the matching...
This paper addresses the problem of defocus map estimation from a single image. We present a fast yet effective approach to estimate the spatially varying amounts of defocus blur at edge locations, which is based on the maximum ranks of the corresponding local patches with different orientations in gradient domain. Such an approach is motivated by the theoretical analysis which reveals the connection...
Feature extraction and matching are two crucial components in person Re-Identification (ReID). The large pose deformations and the complex view variations exhibited by the captured person images significantly increase the difficulty of learning and matching of the features from person images. To overcome these difficulties, in this work we propose a Pose-driven Deep Convolutional (PDC) model to learn...
Many existing person re-identification (PRID) methods typically attempt to train a faithful global metric offline to cover the enormous visual appearance variations, so as to directly use it online on various probes for identity match- ing. However, their need for a huge set of positive training pairs is very demanding in practice. In contrast to these methods, this paper advocates a different paradigm:...
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.