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.
Traditional point tracking algorithms such as the KLT use local 2D information aggregation for feature detection and tracking, due to which their performance degrades at the object boundaries that separate multiple objects. Recently, CoMaL Features have been proposed that handle such a case. However, they proposed a simple tracking framework where the points are re-detected in each frame and matched...
In order to reduce the effects caused by complex environments and ambient light conditions, a fast, robust and effective obstacles detection method of vehicles based on image analysis of multi-feature is proposed. Firstly, regions of interest (ROI) which contain lanes, vehicles and few parts of interference background are extracted in the input image by detecting gradient feature in rows. Secondly,...
Patients with impaired walking function are often dependent on assistive devices to retrain gait and regain independence in life. To provide adequate support, gait rehabilitation devices have to be manually set to the correct support mode or have to recognize the type and starting point of a certain motion automatically. For automated motion type detection, machine learning-based classification algorithms...
It is critical to classify the landing terrain from aerial images when an unmanned aerial vehicle lands at an unprepared site autonomously by using a vision sensor. Owing to the interference of illumination variations and noises, different terrains may show a similar image feature and the same terrain may have a different image feature, which brings great difficulties to image classification. To address...
Efficient and robust detection of humans has received great attention during the past few decades. This paper presents a two-staged approach for human detection in RGB-D images. As the traditional sliding window-based methods for target localization are often time-consuming, we propose to use the super-pixel method in depth data to efficiently locate the plausible head-top locations in the first stage...
Collaborative representation based classifier (CRC) and its probabilistic improvement ProCRC have achieved satisfactory performance in many image classification applications. They, however, do not comprehensively take account of the structure characteristics of the training samples. In this paper, we present an extended probabilistic collaborative representation based classifier (EProCRC) for image...
Text embedded in natural scene images provide rich semantic information about the scene, which is of great value for content-based image applications. Due to the variety of text appearance and the complexity of scene context, however, text detection in natural images remains a challenging task. In this paper, we propose a robust text detection method that hierarchically and progressively localizes...
Robust visual tracking for outdoor vehicle is still a challenging problem due to large appearance variations caused by illumination variation, occlusion and scale variation, etc. In this paper, a deep-learning-based approach for robust outdoor vehicle tracking is proposed. Firstly, a stacked denoising auto-encoder is pre-trained to learn the feature representation way of images. Then, a k-sparse constraint...
Face alignment is a critical topic in the computer vision community. Numerous efforts have been made and various benchmark datasets have been released in recent decades. However, two significant issues remain in recent datasets, e.g., Intra-Dataset Variation and Inter-Dataset Variation. Inter-Dataset Variation refers to bias on expression, head pose, etc. inside one certain dataset, while Intra-Dataset...
With the increasing number of public available training data for face alignment, the regression-based methods attracted much attention and have become the dominant methods to solve this problem. There are two main factors, the variance of the regression target and the capacity of the regression model, affecting the performance of the regression task. In this paper, we present a Stacked Hourglass Network...
Robust hand detection and classification is one of the most crucial pre-processing steps to support human computer interaction, driver behavior monitoring, virtual reality, etc. This problem, however, is very challenging due to numerous variations of hand images in real-world scenarios. This work presents a novel approach named Multiple Scale Region-based Fully Convolutional Networks (MSRFCN) to robustly...
In this paper, we propose a video summarization system for volleyball videos. Our system automatically detects rally scenes as self-consumable video segments and evaluates rally-rank for each rally scene to decide priority. In the priority decision, features representing the contents of the game are necessary; however such features have not been considered in most previous methods. Although several...
Dimensionality reduction is a challenging task for high dimensional data processing in machine learning and data mining. As an effective dimension reduction technique, unsupervised feature selection aims at finding a subset of features to retain the most relevant information. In this paper, we propose a novel unsupervised feature selection method, called Manifold Regularized Robust Unsupervised Feature...
Visual tracking is a significant but challenging field in computer vision. Although considerable progress has been made in recent years, robust tracking in complicated scenes remains an open problem. Trackers get confused easily when similar objects appear or heavy clutter occurs due to indistinguishable features. In this work, a more effective feature extraction method based on convolutional neural...
Every minute, staggering amounts of user-generated videos are uploaded to on-line social networks. These videos can generate significant advertising revenue, providing strong incentive for unscrupulous individuals that wish to capitalize on this bonanza by pirating short clips from popular content and altering the copied media in ways that might bypass detection. Unfortunately, while the challenges...
We propose a novel 3D-assisted coarse-to-fine extreme-pose facial landmark detection system in this work. For a given face image, our system first refines the face bounding box with landmark locations inferred from a 3D face model generated by a Recurrent 3D Regressor at coarse level. Another R3R is then employed to fit a 3D face model onto the 2D face image cropped with the refined bounding box at...
Person re-identification (re-id) aims to match a specific person across non-overlapping views of different cameras, which is currently one of the hot topics in computer vision. Compared with image-based person re-id, video-based techniques could achieve better performance by fully utilizing the space-time information. This paper presents a novel video-based person re-id method named Deep Feature Guided...
Scene-text detection in natural-scene images is an important technique because scene texts contain location information such as names of places and buildings, but many difficulties still remain regarding practical use. In this paper, we tackle two problems of scene-text detection. The first is the discontiguous component problem in specific languages that contain characters consisting of discontiguous...
Identifying the physical person behind an SNS account has become a critical issue in investigations of SNS-involved crime cases. It is a challenging task because information provided by users on an SNS platform could be false, conflicting, missing and deceptive. One way to gain an accurate profile of a user is to link up all their multiple accounts created on different social platforms, which is referred...
Humans can recognise objects under partial occlusion. Machine-based approaches cannot reliably recognise objects and scenes in the presence of occlusion. This paper investigates the use of the elastic net hierarchical MAX (En-HMAX) model to handle occlusions. Our experiments show that the En-HMAX model achieves an accuracy of ∼70%, when ∼50% artificial occlusions are applied to the centre of the visual...
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.