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.
Color mapping for 3D models with captured images is a classical problem in computer vision. Typically, registration between 3D model and images is assumed to be provided, otherwise corresponding points need to be labeled. For many applications, 3D model and images are acquired from different devices, since registration cannot be directly obtained, manual labeling has to be adopted. In this paper,...
Low-cost consumer depth cameras and deep learning have enabled reasonable 3D hand pose estimation from single depth images. In this paper, we present an approach that estimates 3D hand pose from regular RGB images. This task has far more ambiguities due to the missing depth information. To this end, we propose a deep network that learns a network-implicit 3D articulation prior. Together with detected...
It is estimated that the number of devices connected to the Internet will be 50 billion by 2020. How should a not-so-tech-savvy end-user be able to discover, configure, and directly interact with a myriad of connected things in an intuitive and comfortable manner? Even if smartphones and wearables have shown potential for managing IoT environments, we cannot rely on that they can be used for all future...
In this paper, we propose a novel eye-tracking method that uses a multispectral camera to simultaneously track the pupil and recognize the iris. Our hybrid approach leverages existing methods, combining them so as to compensate for weaknesses present in each individual method when used alone. Significantly, our method allows for movements of the center of rotation of the eye to be taken into consideration,...
In this paper, a robust visual tracking system with occlusion handling is proposed to track the target with real-time performance. The thermal camera, which can observe the heat originated from the target such as the human body or vehicle, can collaborate with the color camera to track the target in the cluttered environment or under occlusion. Unlike the general tracking by using the color camera...
Classification of human actions is very challenging and important in many video-based applications. Two common features, i.e., the hand-crafted and the deep-learned ones are usually adopted for video representation and have been proven to be effective in many famous datasets in the literature. However, the hand-crafted feature lacks the ability to detect the discriminative and semantic features and...
In this work, we propose a new multi-color recognition method based on color constancy model, and present a realtime machine vision-based auto-sorting system corresponding to academic and industrial needs. The proposed color constancy computation method is computed by neighborhood contrast, and furthermore the relationship between the object color and the color constancy parameters is established...
The article is devoted to the development of the technical vision system, which is used to control the operation of the harvesting unit of robot for gathering berries. The authors offer technical and software solutions to simplify the maintenance of the robot. Special attention is paid to methods of recognition of wild plants under various external conditions and disturbances.
The state of the art VR/AR devices provide access to completely virtual environments or augment information on the existing world seen by the user. Wearable devices encumber the users, and sometimes even cut them off completely from the real world. Users interact with digital avatars instead of the real people themselves. Spatially augmented reality (SAR) instead focuses on illuminating physical spaces...
This research proposes a convolutional neural network based pupil center detection method from an eye image which is captured by a wearable eye camera. This paper investigates the detection accuracy by applying several preprocessing, such as edge detection, and binarization. We find the preprocess method in order to speed up the computation time. We collected approximately 8,000 eye images with six...
Segmentation process in an essential part in image processing to obtain good preparation either for further process of data mining or object recognition. This paper proposes a new method of segmenting tomato image for clustering its ripeness. The tomato images are taken from three types of smartphone camera in various lighting condition with white background. When taking picture by using smartphone...
Sorting technique is one of the most essential process to differentiate or uniquely identify the required object out of a bulk. It has brought revolutionary change in the automation and manufacturing industry and has further given new dimension to the industry. The project is proposed to sort the pencils on the basis of the color. A conveyor driven system has been used for this particular process...
Rather than being completely isolated, the various human sensory systems can influence each other, sometimes strongly. For example, the cognitive phenomenon known as “colored hearing” involves seeing colors in response to auditory stimuli. This type of special cognitive condition, in which one sensory stimulus evokes a different perception from that of the trigger, is known as “synesthesia.” Previous...
This paper describes a method of grasp point detection from an item of cloth with unarranged shape. We focus on the combination of grasp point detector with shape classifier. In the proposed method, Convolutional Neural Network(CNN) is generated for shape classification, and it is also used for extracting a feature vector that presents shape characteristics. Using the feature, grasp points are calculated...
In this paper, we present an approach to simultaneous localization and mapping (SLAM) for RGB-D cameras like the Microsoft Kinectv2 that is capable of reconstructing volumetric 3D map without the aid of a graphics processing unit (GPU). For many robots, including flying robots and ground mobile robots, most of them build 3D maps, such as sparse or dense point cloud. However, these maps can not give...
The objective of this paper is to propose an algorithm for fusion of images of two different image modalities, i.e., color visual image and its corresponding infrared (IR) image. Fusion method is based on l1 total variation minimization technique, and it combines appearance detail and thermal information for a scene using visual and IR images, respectively. Moreover, the proposed method maintains...
The images taken through glass often capture a target transmitted scene as well as undesired reflected scenes. In this paper, we propose a low-rank matrix completion algorithm to remove reflection artifacts automatically from multiple glass images taken at slightly different camera locations. We assume that the transmitted scenes are more dominant than the reflected scenes in typical glass images...
Single feature of pedestrian is difficult to accurately describe the target using traditional algorithms. A new reidentification algorithm combing global features and local features with different distance metric function is introduced. First, weighted color histogram feature for whole pedestrian is extracted and combined with Bhattacharyya distance to roughly recognize targets. Then pedestrians’...
The Microsoft Kinect sensor has been widely used in many applications, but it suffers from the drawback of low depth accuracy. In this paper, we present a unified depth modification model to improve the Kinect depth accuracy by registering depth and color images in an iterative manner. Specifically, in each iteration, we first establish a coarse correspondence based on the feature descriptor of the...
Frame dropping is a type of video manipulation where consecutive frames are deleted to omit content from the original video. Automatically detecting dropped frames across a large archive of videos while maintaining a low false alarm rate is a challenging task in digital video forensics. We propose a new approach for forensic analysis by exploiting the local spatio-temporal relationships within a portion...
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.