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.
Pedestrian detection is a critical problem in computer vision with significant impact on safety in urban autonomous driving. In this work, we explore how semantic segmentation can be used to boost pedestrian detection accuracy while having little to no impact on network efficiency. We propose a segmentation infusion network to enable joint supervision on semantic segmentation and pedestrian detection...
Monitoring aquatic debris is of great interest to the ecosystems, marine life, human health, and water transport. This paper presents the design and implementation of SOAR—a vision-based surveillance robot system that integrates an off-the-shelf Android smartphone and a gliding robotic fish for debris monitoring in relatively calm waters. SOAR features real-time debris detection and coverage-based...
To detect small target in sea clutter, a method based on local backscattering amplitude prediction error is proposed in the paper. This approach builds on linear prediction: calculating the mean of the fourth power of prediction error of backscattering amplitude. By analyzing the IPIX radar datasets, it is found that the prediction error's mean and variance of the range bin containing a small target...
Monitoring aquatic debris is of great interest to the ecosystems, marine life, human health, and water transport. This paper presents the design and implementation of SOAR — a vision-based surveillance robot system that integrates an off-the-shelf Android smartphone and a gliding robotic fish for debris monitoring. SOAR features real-time debris detection and coverage-based rotation scheduling algorithms...
In radar target detection application fields, rich of information of targets may be included in medium frequency. Doppler shift caused by moving target is one of them. In this paper, Doppler shift and its Short Time Fourier Transform-STFT is analyzed and discussed. Since it is difficult to distinguish the Doppler shift of moving target even in frequency domain with STFF method, fuzzy C means clustering...
The video sequences degraded by fog suffer from poor visibility. In this paper, we present a contrast limited adaptive histogram equalization (CLAHE)-based method to remove fog. CLAHE establishes a maximum value to clip the histogram and redistributes the clipped pixels equally to each gray level. It can limit the noise while enhancing the contrast. First, the background image is extracted from the...
Landmark labeling of training images is essential for many learning tasks in computer vision, such as object detection, tracking, and alignment. Image labeling is typically conducted manually, which is both labor-intensive and error-prone. To improve this process, this paper proposes a new approach to estimate a set of landmarks for a large image ensemble with only a small number of manually labeled...
Wavelet-based fractal scaling analysis is a new method based on fractal geometry for detecting small targets within sea clutter. But the fractal dimension of sea clutter is affected by not only the presence of a target but also sea wave propagation directions, which will degrade accuracy of detection under various sea and weather conditions. An improved method using spatial Hurst parameter differences...
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.