- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
An FPGA-Oriented Algorithm for Real-Time Filtering of Poisson Noise in Video Streams, with Application to X-Ray Fluoroscopy
摘要： In this paper we propose a new algorithm for real-time ?ltering of video sequences corrupted by Poisson noise. The algorithm provides effective denoising (in some cases overcoming the ?ltering performances of state-of-the-art techniques), is ideally suited for hardware implementation, and can be implemented on a small ?eld-programmable gate array using limited hardware resources. The paper describes the proposed algorithm, using X-ray ?uoroscopy as a case study. We use IIR ?lters for time ?ltering, which largely simpli?es hardware cost with respect to previous FIR ?lter-based implementations. A conditional reset is implemented in the IIR ?lter, to minimize motion blur, with the help of an adaptive thresholding approach. Spatial ?ltering performs a conditional mean to further reduce noise and to remove isolated noisy pixels. IIR ?lter hardware implementation is optimized by using a novel technique, based on Steiglitz–McBride iterative method, to calculate ?xed-point ?lter coef?cients with minimal number of nonzero elements. Implementation results using the smallest StratixIV FPGA show that the system uses only, at most, the 22% of the resources of the device, while performing real-time ?ltering of 1024 × 1024@49fps video stream. For comparison, a previous FIR ?lter-based implementation, on the same FPGA, in the same conditions and constraints (1024 × 1024@49fps), requires the 80% of the logic resources of the FPGA.
关键词： Poisson noise,X-ray video?uoroscopy processing,Field-programmable gate array (FPGA),IIR ?ltering,IIR ?lter design,Real-time video ?ltering
更新于2025-09-23 15:22:29
-
[IEEE 2018 2nd International Conference on Trends in Electronics and Informatics (ICOEI) - Tirunelveli (2018.5.11-2018.5.12)] 2018 2nd International Conference on Trends in Electronics and Informatics (ICOEI) - SmartMobiCam: Towards a New Paradigm for Leveraging Smartphone Cameras and IaaS Cloud for Smart City Video Surveillance
摘要： Cloud and mobile computing domains have become quite popular these days. Besides, the ubiquitous smartphones are increasingly becoming a dominant platform for collaborative sensing, so we built an android application SmartMobiCam, which aids in forming the robust and scalable Smart city video surveillance system which is critical for upgrading the urban areas. The application obtains video feed, images and sound clips from the users and then uses cloud services for video enhancement and restoration of the content and provides it to all subscribers including police investigators. The application is explained with detailed architectural and technological choices. Performance analysis shows that the proposed application performs well and outperforms the traditional surveillance system.
关键词： waiting time,video enhancement,Smart city Surveillance,SmartMobiCam,Cloud Mobile Computing
更新于2025-09-23 15:22:29
-
[IEEE 2018 IEEE International Conference on Internet of Things and Intelligence System (IOTAIS) - BALI, Indonesia (2018.11.1-2018.11.3)] 2018 IEEE International Conference on Internet of Things and Intelligence System (IOTAIS) - Ultra-low-latency Video Coding Method for Autonomous Vehicles and Virtual Reality Devices
摘要： Applications such as autonomous driving and virtual reality (VR) require low-latency transfer of high definition (HD) video. The proposed ultra-low-latency video coding method, which adopts line-based processing, has 0.44μs latency at minimum for Full-HD video. With multiple line-based image-prediction methods, image-adaptive quantization, and optimized entropy coding, the proposed method achieves compression to 39.0% data size and image quality of 45.4dB. The proposed basic algorithm and the optional 1D-DCT mode achieve compression to 33% and 20%, respectively, without significant visual degradation. These results are comparable to those for H.264 Intra despite one-thousandth ultra-low-latency of the proposed method. With the proposed video coding, the autonomous vehicles and VR devices can transfer HD video using 20% of the bandwidth of the source video without significant latency or visual degradation.
关键词： low latency,video coding,virtual reality (VR),autonomous driving
更新于2025-09-23 15:22:29
-
[IEEE 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Chongqing (2018.6.27-2018.6.29)] 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC) - Distributed Compressive Video Sensing with Adaptive Reconstruction Based on Temporal Correlation
摘要： Aiming at enhance reconstruction quality, this paper proposes an adaptive reconstruction scheme with no feedback channel for distributed compressive video sensing, effectively exploiting temporal correlation. Specifically, the proposed scheme divides each block of non-key frames into different classifications based on temporal correlation in the encoding side and selects corresponding reconstruction mode which adaptively utilizes side information in the decoding side. The simulation results show that the proposed scheme achieves superior performance over existing methods in terms of reconstruction quality and computation cost.
关键词： adaptive reconstruction,distributed compressive video sensing,temporal correlation
更新于2025-09-23 15:22:29
-
High-Resolution ENT Video Endoscope with Superior Image Quality Equivalent to that of Gastric Video Endoscopes
摘要： Background and study aims: To assess the usability of high resolution fiberscope which has equivalent image quality to that of the esophageal and gastric video endoscopes. Patients and methods: Image resolution of this endoscope was estimated by the United States Air Force (USAF) resolution test chart. Clinical application was done between January and December 2010 and transnasal observation of the larynx and hypopharynx were performed during this period. These examinations were done for screening and follow-up for patients with hypopharyngeal and laryngeal disorders. Results: This endoscope could distinguish features on a scale of nearly 20 μm, and abnormal vascular patterns on the mucosal surface characteristic of carcinomas were clearly observed under a conventional light source. In addition, these changes on the mucosal surface became more apparent with use of the i-SCAN?. Nevertheless, the handling of this video endoscope was similar to that of popular ENT video endoscopes, and all patients tolerated its use well. Conclusion: This new device may dramatically improve pharyngolaryngeal examination in ENT clinics.
关键词： Narrow-band imaging,Intraepithelial papillary capillary loops,Early diagnosis,Video endoscope
更新于2025-09-23 15:22:29
-
[IEEE 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - Krakow, Poland (2018.10.16-2018.10.18)] 2018 IEEE International Conference on Imaging Systems and Techniques (IST) - A Temporal Tone Mapping Adaptation: An Application using Logarithmic Camera
摘要： Noise, ?icker, temporal inconsistencies disturb the tone mapping creation for High Dynamic Range image (HDR). A method to alleviate these artifacts in tone mapped HDR video sequences is presented in this paper. A temporal ?ltering is developed in order to minimize undesirable artifacts in the low dynamic range image reconstruction process. In the experiments, tone mapping is applied on video sequences obtained by a logarithmic camera. This temporal process provides visual comfort without any kind of blink and prevents Low Dynamic Range (LDR) videos to be disturbed by some random brightness values of isolated pixels.
关键词： logarithmic sensor,temporal artifacts,high dynamic range video,tone mapping
更新于2025-09-23 15:22:29
-
Generalized Content-Preserving Warp: Direct Photometric Alignment beyond Color Consistency
摘要： Motion estimation is vital in many computer vision applications. Most existing methods require high quality and large quantity of feature correspondence, and may fail for images with few textures. In this paper, a photometric alignment method is proposed to obtain better motion estimation result. Since the adopted photometric constraints are usually limited to required illumination or color consistency assumption, a new Generalized Content-Preserving Warp (GCPW) framework therefore is designed to perform photometric alignment beyond color consistency. Similar to conventional Content-Preserving Warp (CPW), GCPW is also a mesh-based framework, but it extends CPW by appending a local color transformation model for every mesh quad, which expresses the color transformation from a source image to a target image within the quad. Motion-related mesh vertexes and color-related mapping parameters are optimized jointly in GCPW to get more robust motion estimation result. Evaluation of tens of videos reveals that the proposed method achieves more accurate motion estimation results. More importantly, it is robust to significant color variation. Besides, this paper explores the performance of GCPW in two popular computer vision applications: image stitching and video stabilization. Experimental results demonstrate GCPW's effectiveness in dealing with typical challenging scenes for these two applications.
关键词： Color Difference,Video Stabilization,Photometric Constraint,Image Stitching,Motion Estimation
更新于2025-09-23 15:21:21
-
[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) - A Machine Learning Approach to Accurate Sequence-Level Rate Control Scheme for Video Coding
摘要： In this paper, we propose a two-pass encoding framework to handle the problem of sequence-level rate control. We consider the sequence-level encoding parameter constant rate factor (CRF) as the factor to be adjusted. The proposed framework mainly has two key contributions. First, we provide a second order model to characterize the relationship between the bitrate and CRF. The proposed second order model outperforms the traditional linear model significantly. Second, we adopt a shallow neural network to train the relationship between the content-dependent features with the second-order model parameters. The proposed neural network is quite simple but able to estimate the model parameters accurately. We implement the proposed algorithm under tensorflow. Experimental results show that our proposed method obviously outperforms the state-of-the-art method.
关键词： sequence-level,constant rate factor,video coding,Rate control,Machine learning,second order model
更新于2025-09-23 15:21:21
-
Automatic Detection of Driver Impairment Based on Pupillary Light Reflex
摘要： The main objective of this paper is to determine the feasibility of designing a driver drunkenness detection system based on the dynamic analysis of a subject’s pupillary light reflex (PLR). This involuntary reaction is widely utilized in the medical field to diagnose a variety of diseases, and in this paper, the effectiveness of such a method to reveal an impairment condition due to alcohol abuse is evaluated. The test method consists in applying a light stimulus to one eye of the subject and to capture the dynamics of constriction of both eyes; for extracting the pupil size profiles from the video sequences, a two-step methodology is described, where in the first phase, the iris/pupil search within the image is performed, and in the second stage, the image is cropped to perform pupil detection on a smaller image to improve time efficiency. The undesired pupil dynamics arising in the PLR are defined and evaluated; a spontaneous oscillation of the pupil diameter is observed in the range [0, 2] Hz and the accommodation reflex causes pupil constriction of about 10% of the iris diameter. A database of pupillary light responses is acquired on different subjects in baseline condition and after alcohol consumption, and for each one, a first-order model is identified. A set of features is introduced to compare the two populations of responses and is used to design a support vector machine classifier to discriminate between “Sober” and “Drunk” states.
关键词： pupil dynamics,video processing,system identification,ADAS,support vector machine,classification
更新于2025-09-23 15:21:21
-
Large-Field-of-View Visualization Utilizing Multiple Miniaturized Cameras for Laparoscopic Surgery
摘要： The quality and the extent of intra-abdominal visualization are critical to a laparoscopic procedure. Currently, a single laparoscope is inserted into one of the laparoscopic ports to provide intra-abdominal visualization. The extent of this ?eld of view (FoV) is rather restricted and may limit ef?ciency and the range of operations. Here we report a trocar-camera assembly (TCA) that promises a large FoV, and improved ef?ciency and range of operations. A video stitching program processes video data from multiple miniature cameras and combines these videos in real-time. This stitched video is then displayed on an operating monitor with a much larger FoV than that of a single camera. In addition, we successfully performed a standard and a modi?ed bean drop task, without any distortion, in a simulator box by using the TCA and taking advantage of its FoV which is larger than that of the current laparoscopic cameras. We successfully demonstrated its improved ef?ciency and range of operations. The TCA frees up a surgical port and potentially eliminates the need of physical maneuvering of the laparoscopic camera, operated by an assistant.
关键词： large ?eld of view,laparoscopy,video stitching,surgical skills,miniaturized cameras,bean drop task
更新于2025-09-23 15:21:21