- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Recognition and tracking of moving objects in the images captured by UAV intelligently in earth observation operations
摘要： Today, drone is used for different purposes. Among these, security through detecting and tracking moving vehicles that have violated traffic rules, developing photo coverage from vast and high-risk areas, helping out deprived areas, and so on can be mentioned. In this paper, a new method is presented for detecting and tracking moving objects from moving platforms. The process itself consists of two parts: (1) identifying the path range that the object moves, which helps eliminate excess margins and increase the speed of operations and (2) identifying moving objects inside the path range and tracking them with a new method, which helps increase the accuracy in this regard. The approach presented to the selected video is applied to a frame as large as (1280 × 720) and has yielded very satisfactory results. Thus, the ability to identify the given moving objects in this method is 66% and 75% in very crowded scenes and in very quiet scenes, respectively. However, the power of the conventional methods in this regard is about 21% and 50% in the scenes with very busy backgrounds and in the scenes with very quiet backgrounds, respectively.
关键词： UAV,Identification of moving objects,Tracking of moving objects,Earth observation,Video images
更新于2025-09-10 09:29:36
-
Centroid tracking and velocity measurement of white blood cell in video
摘要： Automated blood cells tracking system has a vital role as the tracking process reflects the blood cell characteristics and indicates several diseases. Blood cells tracking is challenging due to the non-rigid shapes of the blood cells, and the variability in their videos along with the existence of different moving objects in the blood. To tackle such challenges, we proposed a green star based centroid (GSBC) moving white blood cell (WBC) tracking algorithm to measure its velocity and draw its trajectory. The proposed cell tracking system consists of two stages, namely WBC detection and blob analysis, and fine tuning the tracking process by determine the centroid of the WBC, and mark the centroid for further fine tracking and to exclude the bacteria from the bounding box. Furthermore, the speed and the trajectory of the WBC motion are recorded and plotted. In the experiments, an optical flow technique is compared with the proposed tracking system showing the superiority of the proposed system as the optical flow method failed to track the WBC. The proposed system identified the WBC accurately, while the optical flow identified all other objects lead to its disability to track the WBC.
关键词： Trajectory analysis,Video processing,Cell detection,Velocity measurements,Blob analysis,White blood cell,Tracking system
更新于2025-09-10 09:29:36
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Temporal Attention Network for Action Proposal
摘要： Temporal action proposal, which extracts segments of interests from untrimmed video, is an important step for video analysis. For state-of-the-art temporal action proposal methods, average pooling is often used to aggregate features in deep neural networks, which inevitably ignores the significances of different video clips. Therefore, we propose a Temporal Attention Network (TAN) model to address this issue. Temporal attention with fully connected layers is introduced to adaptively combine clip-level features and form a compact and discriminative video representation. In addition, we show that the learned attention weights could also be used as an effective temporal feature to further improve the performance. Extensive experiments on THUMOS-14 demonstrate that our algorithm performs favorably against the state-of-the-art methods.
关键词： untrimmed video analysis,Temporal action proposal,neural network,temporal attention
更新于2025-09-10 09:29:36
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - An Efficient Image Formation Algorithm for Spaceborne Video SAR
摘要： To avoid unnecessary duplication of processing and meet the real-time requirement of video SAR. An image formation algorithm of spaceborne video SAR based on sub-aperture extended chirp scaling processing was proposed in this paper. Firstly the SAR raw data segmentation approach was presented to realize the SAR video frames continuous output. Then the raw data of a video frame was divided to several sub-apertures, after the extended CS processing in the sub-apertures, the frequency sub-bands of sub-apertures were combined to achieve the desired high azimuth resolution video SAR frames. This innovative image formation algorithm can avoid the duplication of processing, so as to improve computation efficiency. Finally, experiments on simulated data show that the proposed algorithm is effective.
关键词： spaceborne video SAR,extended chirp scaling algorithm,data overlap,sub-aperture processing
更新于2025-09-10 09:29:36
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Shadow Tracking of Moving Target Based on CNN for Video SAR System
摘要： Fast Moving targets always are shifted or smeared outside the scene in different images sequence to make video by Circle Synthetic Aperture Radar (SAR).In this paper, a novel moving target tracking approach with the shadow detection and tracking (SDT) is presented based on Convolution Neural Network. Based on the shadow characteristic of moving target in SAR imagery, CNN tracking classification is employed on potential moving target candidates extracted from a sequence of temporal and spatial sub-aperture SAR images to detect and track the moving targets. By the simulation experiments and performance analysis, the validity of the proposed algorithm can be demonstrated. Real data set processing results are provided to demonstrate the effectiveness of the proposed approach.
关键词： Video SAR,Convolution Neural Network,Shadow detection,Moving target tracking
更新于2025-09-10 09:29:36
-
Automated, continuous video microscopy tracking of hyphal growth
摘要： The growth of filamentous fungi is a complex process that involves hyphal elongation and branching. Microscopic observations provide a wealth of information on fungal growth, although often requiring laborious manual intervention to record and analyze images. Here, we introduce a novel tool for automated tracking of growth in fungal hyphae that affords quantitative analysis of growth rate and morphology. We supplied a student-grade bright field microscope with stepper motors to enable computer-control of the microscope stage. In addition, we developed an image-processing routine that detects in real-time the tip of a hypha and tracks it as the hypha elongates. To achieve continuous observation of hyphal growth, our system automatically maintains the observed sample within field-of-view and performs periodic autofocus correction in the microscope. We demonstrate automated, continuous tracking of hyphal growth in Trichoderma atroviride with sampling rates of seconds and observation times of up to 14 h. Tracking records allowed us to determine that T. atroviride hyphae grow with characteristic elongation rates of ~70 nm/s. Surprisingly, we found that prior to the occurrence of an apical branching event the parental hypha stopped growing during a few minutes. These arrest events presented occasionally for subapical branching as well. Finally, from tracking data we found that the persistence length (a measure of filament extension before presenting a change in direction) associated to T. atroviride hyphae is 362 μm. Altogether, these results show how integration of image analysis and computer control enable quantitative microscopic observations of fungal hyphae dynamics.
关键词： automated tracking,video microscopy,persistence length,Hyphal growth,branching
更新于2025-09-10 09:29:36
-
Synchronous 2D/3D Switching System for Service-Compatible 3DTV Broadcasting
摘要： This paper proposes a new broadcasting system for the service-compatible 3DTV in which the 3D service can coexist with the conventional digital TV broadcast. In the proposed system, the commercial 3DTV service can be implemented via the existing DTV channel without utilizing the dedicated 3DTV system. This 2D/3D system interworks with the conventional system and can switch to 2D or 3D service according to the broadcast programming and schedule. The system also provides a mechanism that can prevent the synchronization mismatch between left and right video streams and between the stream and the associated signaling in the 2D/3D transition periods. The picture quality measurements are carried out based on the ITU-R recommended test to check the level of quality of service provided by the proposed scheme. The conformity tests are also performed with the conventional channel and the receiver for the DTV system to confirm the feasibility of the proposed one for the commercial service.
关键词： 3DTV,video quality,service-compatible,3D multiplexer,2D/3D switch
更新于2025-09-10 09:29:36
-
Depth estimation from infrared video using local-feature-flow neural network
摘要： Depth estimation is essential for infrared video processing. In this paper, a novel depth estimation method, called local-feature-flow neural network (LFFNN), is proposed for generating depth maps for each frame of an infrared video. LFFNN extracts local features of a frame with the addition of inter-frame features, which is extracted from the previous frames on the corresponding region in the infrared video. LFFNN is designed for extracting the local features flow in the infrared video, learning better depth-related features through three control gates by inter-frame features propagation as the video progresses. After feature extraction, a pixel-level classifier is created to estimate depth level of different pixels in the infrared video. Our proposed approach achieves state-of-the-art depth estimation performances on the test dataset.
关键词： Infrared video,Depth estimation,Sequence learning,Neural network
更新于2025-09-10 09:29:36
-
Asymmetric photic driving response: importance of reviewing the video
摘要： Intermittent photic stimulation (IPS) is commonly used during electroencephalography to detect abnormal epileptogenic sensitivity to flickering light. In practice, substantial variability is found depending on the practice of the laboratory. We report a patient who had inadvertent medical investigations due to inappropriate photic stimulation.
关键词： intermittent photic stimulation,video review,photic driving response,epilepsy,electroencephalography
更新于2025-09-10 09:29:36
-
PeQASO: Perceptual Quality Assessment of Streamed Videos Using Optical Flow Features
摘要： In this paper, we introduce PeQASO, a perceptual quality assessment framework for streamed videos using optical ?ow features. This approach is a reduced-reference pixel-based and relies only on the deviation of the optical ?ow of the corrupted frames. This technique compares an optical ?ow descriptor from the received frame against the descriptor obtained from the anchor frame. This approach is suitable for videos with complex motion patterns. Our technique does not make any assumptions on the coding conditions, network loss patterns or error concealment techniques. In this paper, we consider both sources of artifacts and distortions in streaming, including compression artifacts. We validate our proposed metric by testing it on a variety of distorted sequences from three proposed and commonly utilized video quality assessment databases. Our results show that our metric estimates the perceptual quality at the sequence level accurately. We report the correlation coef?cients with the differential mean opinion scores reported in the database. For compression artifacts, the results show Spearman’s and Pearson’s correlations of 0.96 and 0.94 for all the tested sequences, respectively. For channel-induced distortion, the results show Spearman’s and Pearson’s correlations of 0.88 and 0.89, respectively. For all other distortions, the average Spearman’s and Pearson’s correlations are 0.82 and 0.79, respectively.
关键词： Video quality assessment,optical ?ow,video streaming,video coding,channel losses,video quality monitoring,video distortion
更新于2025-09-09 09:28:46