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 (re-id) aims to match people across non-overlapping camera views. So far the RGB-based appearance is widely used in most existing works. However, when people appeared in extreme illumination or changed clothes, the RGB appearance-based re-id methods tended to fail. To overcome this problem, we propose to exploit depth information to provide more invariant body shape and skeleton...
Video summarization refers to the process of recapitulating video stream by producing an abstract of the salient keyframes that could cover its overall content. However, an efficient video summarization requires an efficient video Shot Boundary Detection (SBD) and keyframes extraction. In this backdrop, this paper presents a novel and efficient approach for video SBD and keyframes extraction that...
Text separation in natural scenes is a crucial step to recognize scene text. Since computational power in a mobile device is limited, current text extraction methods are impractical in real-time devices. We propose efficient text extraction methods by utilizing user's indication. When user simply indicates focus or draws the line on touch screen, the system can extract text in natural scenes efficiently...
In this paper, a hybrid algorithm for precise eyes localization in color facial region is presented. In practice, most eye detection suffer from the influence of illumination and face pose. Multiple techniques are integrated in this algorithm to overcome these limitations, such as color space mapping, illumination correction, mouth detection, dynamic threshold and so on. The scheme consists of two...
Due to the existence of complicated illumination, background and variations of pose, fast and robust face detection is constrained in many applications. This paper describes a novel scheme conceived to integrate multiple cues to detect face under in-plane rotation, Concretely, we apply skin-color, heuristic rules and eye feature to build a robust detector. First, skin detection approach based on novel...
This paper presents an evaluation of the SIFT (scale invariant feature transform), Colour SIFT, and SURF (speeded up robust feature) descriptors on very low resolution images. The performance of the three descriptors are compared against each other on the precision and recall measures using ground truth correct matching data. Our experimental results show that both SIFT and colour SIFT are more robust...
Illumination estimation for color constancy is an important problem in computer vision. Existing algorithms can be divided into two groups: physics-based algorithms and statistics-based approaches. In this paper, the advantages of the two kinds are integrated. At first, a novel statistic-based algorithm called Illumination Estimation using K-nearest-neighbor (IE-KNN) is proposed. And then the physics-based...
Computer vision systems used on road maintenance, either related to signs or to the road itself, are playing a major role in many countries because of the higher investment on public works of this kind. These systems are able to collect a wide range of information automatically and quickly, with the aim of improving road safety. In this context, the suitability of the information contained on the...
A horizon extraction method in ocean observation is proposed. Extracting the horizon correctly from the sea images automatically is a challenge task in ocean environment due to the change of lighting or other diversified conditions. The approach converts a color image to a gray scale image with a fusion scheme of nine color channels, and the conversion is insensitive to the variation of light. The...
One of important subjects for mobile robots is the vision based decision-making system with environmental recognition. In order to extract features from obtained images, how to realize color constancy by adjusting color property is the important technical issue. We have been working on color constancy vision algorithms using bio-inspired information processing methods as self-organizing map (SOM),...
In this paper we have designed a neural network based movie genres classifier. The Movie classifier characterizes the movie clips into different movie genres. The characterization is based on low level audio-visual features. We have extracted the computable audio-visual features from the movie clips which are inspired by the techniques and film grammars used by many filmmakers to endow specific characteristics...
In the robot vision, the color is the essential information in the object recognition and cognition process. Here proposed one kind object identification algorithm based on the color characteristic with the YUV color space, uses the study - expansion algorithm to obtain the spatial distribution of the compatible object color characteristic, overcomes the influence that the environment illumination...
Video shot detection is an important contemporary problem since it is the first step toward automatic indexing, content based video retrieval and many other different applications. A novel shot boundary detection using wavelet and Support Vector Machine is proposed in this paper. Shot boundary detection algorithms work by extracting the color and the edge in different direction from wavelet transition...
Background modeling is a key step of background subtraction methods used in the context of static camera. The goal is to obtain a clean background and then detect moving objects by comparing it with the current frame. This paper describes a novel fuzzy approach for moving object detection which is capable of processing images extremely rapidly and achieving high detection rates. This work integrates...
Robust extraction of text from scene images is essential for successful scene text recognition. Scene images usually have non-uniform illumination, complex background, and existence of text-like objects. The common assumption of a homogeneous text region on a nearly uniform background cannot be maintained in real applications. We proposed a text extraction method that utilizes user's hint on the location...
Content-based multimedia database indexing and retrieval tasks require automatic extraction of descriptive features that are relevant to the subject materials i.e., images, video etc. The typical low-level features that are extracted in images and video include measures of color, texture, or shape. Although these features can easily be obtained, they do not give a precise idea of the image content...
Automatic number plate recognition is a real time embedded system which automatically recognizes the license number of vehicles. Such systems require the localization of number plate area in order to identify the characters present on it. This paper presents a feature based methodology for localization of Indian number plates. Since number plate standards are not strictly practiced in India, a large...
Automatic detection of damaged buildings from aerial and satellite images is an important problem for rescue planners and military personnel. In this study, we present a novel approach for automatic detection of damaged buildings in color aerial images. Our method is based on color invariants for building rooftop segmentation. Then, we benefit from grayscale histogram to extract shadow segments. After...
In bad weather, such as foggy, the vision become poor, and this often induce many problems for traffic safety. So it is a hot research subject how to improve the vision ability for bad weather in traffic, and there are many achievements have been made. Among these the single scale Retinex algorithm is a common used method, which was proposed by Land. According this theory, any obtained image can be...
Local image descriptors computed in areas around salient points in images are essential for many algorithms in computer vision. Recent work suggests using as many salient points as possible. While sophisticated classifiers have been proposed to cope with the resulting large number of descriptors, processing this large amount of data is computationally costly. In this paper, computational methods are...
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.