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.
Object detector with region proposal networks such as Fast/Faster R-CNN [1, 2] have shown the state-of-the art performance on several benchmarks. However, they have limited success for detecting small objects. We argue the limitation is related to insufficient performance of Fast R-CNN block in Faster R-CNN. In this paper, we propose a refining block for Fast R-CNN. We further merge the block and...
Feature selection for regression problems can be highly beneficial in terms of robustness and execution speed. The Correlation-based Feature Selection (CFS) algorithm, in the attempt to find the best feature subset, evaluates different subsets and selects the one with the highest “goodness”. Such goodness is based on the co-relation between the addition of all features in the subset with the output...
Depth-Image-Based Rendering (DIBR) is a mature and important method for making free-viewpoint videos. As for the study of the DIBR approach, on the one hand, most of current research focuses on how to use it in systems with low resolution cameras, while a lot of Ultra HD rendering devices have been launched into markets. On the other hand, the quality and accuracy of the depth image directly affects...
The detection of salient objects in video sequence is an active research area of computer vision. One approach is to perform joint segmentation of objects and background in each image frame of the video. The background scene is learned and modeled. Each pixel is classified as background if it matches the background model. Otherwise the pixel belongs to a salient object. The segregation method faces...
Indoor navigation of unmanned vehicles in GPS denied environment is challenging but a necessity in many real-world applications. Although fully autonomous indoor navigation has been shown to work using simultaneous localization and mapping (SLAM), its accuracy and robustness are inadequate for commercial applications. A semi-autonomous approach is an option for indoor navigation can be achieved using...
Yu et al.[1] showed that dilated convolutions are very effective in dense prediction problems such as semantic segmentation. In this work, we propose a new ResNet[2] based convolutional neural network model using dilated convolutions and show that this model can achieve lower error rate for image classification than ResNet with reduction of the number of the parameters of the network by 94% and that...
Xylem vessels play a pivotal role in plant adaptation to drought stress. In this paper, we propose a novel framework that associates automatic segmentation of xylem vessels with its morphological features as a quantitative proxy to predict drought stress response (DSR). We develop an image processing pipeline that comprises of low level processing which enables high-throughput detection of xylem vessels...
Pedestrian navigation has become one of the most used services in people's city lives. Not only smartphone based navigation, but also the application in the next generation of intelligent wearable devices, such as smart glasses, attract attentions from both scientists and engineers. The satisfied navigation service requires an accurate positioning technology. Even though the current smartphones have...
This paper deals with image segmentation when the image consists of uniform background (b.g.) and uniform foreground (f.g.) with noise. We formulate this problem into the joint minimization of MRF energy with respect to a label image and density parameters corresponding to f.g. and b.g., and solve it exactly in reasonable computation time. The proposed method efficiently solves the joint minimization...
High frame rate and ultra-low delay image processing system plays an increasingly important role in human-machine interactive applications which call for a better experience. Current works based on vision chip target on video with simple patterns or simple shapes in order to get a higher speed, while a more complicated system is required for real-life applications. This paper proposes a BRIEF based...
This paper presents a system that automatically converts 2D raster images to sketch style. The proposed method first extracts edges at different resolutions. Then, these shapes and brightness are varied and merged. This process expresses trial and error in the actual sketch. Experimental results showed that the proposed method produces images with natural appearance.
The Raspberry Pi single-board computer is a low cost, light weight system with small power requirements. It is an attractive embedded computer vision solution for many applications, including that of UAVs. Here, we focus on the Raspberry Pi 2 and demonstrate that, with the addition of a multiplexer and two camera modules, it is able to execute a full stereo matching pipeline, making it a suitable...
This paper introduces a novel idea of unsupervised hotspots detection from first person vision (FPV) records. The purpose is to gather typical patterns of machine operations based on touching or manipulating those hotspots and summarize the patterns as guides for operations such as online operating manuals. We chose sewing machine operation as an example and demonstrated that, a good performance of...
In this contribution, the experimental results of testing a monocular visual odometry algorithm in a real rover platform over flat terrain for localization in outdoor sunlit conditions are presented. The algorithm computes the three-dimensional (3D) position of the rover by integrating its motion over time. The motion is directly estimated by maximizing a likelihood function that is the natural logarithm...
This paper presents a novel single image super resolution (SR) based on a content-aware consstraint and an intensity-order constraint. The proposed method, generates an SR image by minimizing an energy that consists of a data term, the content-aware constraint and the intensity-order constraint. The content-aware constraint can preserve texture patterns while reducing noise in a smooth region, while...
This paper proposes a fast recognition method based on generalized similarity measure (GSM). The GSM achieves good recognition accuracy for face recognition, but has a scalability problem. Because the GSM method requires the similarity measures between a query and all samples to be calculated, the computational cost for recognition is in proportion to the number of samples. A reasonable approach to...
A single PTZ Camera Based People-Occupancy Estimation System (PCBPOES) is proposed to estimate the number of people occupying a region of interest with acceptable accuracy. The PTZ camera aids this objective by efficiently monitoring a wide area by dividing it into zones, capturing high resolution zone images aided by the optical zoom for detecting human head patterns. A seminar room is used as a...
The present study attempts to develop a machine vision system for continuous monitoring of grades of iron ores during transportation through conveyor belts. The machine vision system was developed using the support vector regression (SVR) algorithm. A radial basis function (RBF) kernel was used for the development of optimized hyperplane by transforming input space into large dimensional feature space...
We present a fully convolutional network(FCN) based approach for color image restoration. FCNs have recently shown remarkable performance for high-level vision problem like semantic segmentation. In this paper, we investigate if FCN models can show promising performance for low-level problems like image restoration as well. We propose a fully convolutional model, that learns a direct end-to-end mapping...
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.