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.
Person re-identification, aiming to match a specific person among non-overlapping cameras, has attracted plenty of attention in recent years. It can be regarded as a visual retrieval task, namely given a query person image, ranking all gallery images according to their similarities to the query. Conventionally, this similarity function is learnt by forcing intra-distances to be small while inter-distances...
This paper proposes an effective Temporally Aligned Pooling Representation (TAPR) for video-based person re-identification. To extract the motion information from a sequence, we propose to track the superpixels of the lowest portions of human. To perform temporal alignment of videos, we propose to select the “best” walking cycle from the noisy motion information according to the intrinsic periodicity...
In this paper, we address the problem of person reidentification (re-id), which remains to be challenging due to view point changes, pose variations, different camera settings, etc. Different from common methods that concatenate descriptors extracted from different support regions and feature channels directly as a long vector, we encode the importance of different feature channels and support regions...
Most of types of laser distance measuring instrument cost hundreds of thousand dollars such as Laser scanner or Depth Camera that generates depth maps of space very fast. And the handling is too complicated for non-professional users. So the utilization of 3D reconstruction is very limited. This article introduces a workflow of 3D reconstruction using a new cheaper instrument, the Microsoft Kinect...
To overcome the problem of registration error accumulation, this paper presents a fast video mosaic approach especially suitable for real-time observation of large static scenes. Different from the traditional video mosaic algorithm based on pair-wise local registration, the proposed new approach can directly compute the projective transform between the current input image and the panoramic image,...
Following the economy of our country rapidly develops in recent years, more and more people possess vehicles of their own, and the number of urban vehicle is increasing fast as well. All of these directly challenge the management of urban traffic and normalization of driving behavior. According to actual request for urban traffic, Vehicle Supervision System Based on MEMS Geomagnetic Sensor, for short...
Learning is an integral part of an intelligent agent's problem-solving ability. Most research works on learning assume that information are provided in a complete and well-structured manner and/or when rules are clearly specified, therefore have difficulties in handling cases with incomplete and unstructured data. This paper presents a novel approach to deal with this difficulty. It uses information...
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.