Video-rate Processing Research Articles

High-accuracy and video-rate lifetime extraction from time correlated single photon counting data on a graphical processing unit

Graphical Processing Units (GPUs) are a powerful alternative to central processing units, especially for data-parallel, video-rate processing of large data volumes. In the complex scenario of high-performance, multichannel Time Correlated Single Photon Counting (TCSPC), a huge amount of data is potentially generated by the acquisition system. Exploiting a dedicated, external, programmable elaboration unit enables a high degree of flexibility to perform different types of analysis. In this paper, we present a GPU-based application that leverages the common unified device architecture application programming interface for video-rate and accurate lifetime extraction from TCSPC data acquired at a rate of up to 10 Gbit/s.

Video-rate processing in tomographic phase microscopy of biological cells using CUDA.

We suggest a new implementation for rapid reconstruction of three-dimensional (3-D) refractive index (RI) maps of biological cells acquired by tomographic phase microscopy (TPM). The TPM computational reconstruction process is extremely time consuming, making the analysis of large data sets unreasonably slow and the real-time 3-D visualization of the results impossible. Our implementation uses new phase extraction, phase unwrapping and Fourier slice algorithms, suitable for efficient CPU or GPU implementations. The experimental setup includes an external off-axis interferometric module connected to an inverted microscope illuminated coherently. We used single cell rotation by micro-manipulation to obtain interferometric projections from 73 viewing angles over a 180° angular range. Our parallel algorithms were implemented using Nvidia's CUDA C platform, running on Nvidia's Tesla K20c GPU. This implementation yields, for the first time to our knowledge, a 3-D reconstruction rate higher than video rate of 25 frames per second for 256 × 256-pixel interferograms with 73 different projection angles (64 × 64 × 64 output). This allows us to calculate additional cellular parameters, while still processing faster than video rate. This technique is expected to find uses for real-time 3-D cell visualization and processing, while yielding fast feedback for medical diagnosis and cell sorting.

Video-rate calculation of depth from defocus on a FPGA

Depth from defocus is a ranging method that provides depth estimation at every pixel in an image. It uses a pair of defocused images from a conventional monocular camera. To enable video-rate processing, which is important for industrial applications, an established algorithm was implemented on a field programmable gate array (FPGA). A bifurcating pipeline of 2-D filters provided the depth calculation. Multiplier and SRAM facilities on the FPGA were utilised efficiently by exploiting the filter symmetry. The coefficient and data bit-widths were limited to improve efficiency. The results compared favourably with the full width calculation. Range images were processed within 14 ms.

LSO-AdaBoost Based Face Detection for IP-CAM Video

The IP-CAM plays a major role in the context of digital video surveillance systems. The function of face detection can add extra value and can contribute towards an intelligent video surveillance system. The cascaded AdaBoost-based face detection system proposed by Viola can support real-time detection with a high detection rate. The performance of the Alt2 cascade (from OpenCV) in an IP-CAM video is worse than that with regard to static images because the training data set in the Alt2 cannot consider the localized characters in the special IP-CAM video. Therefore, this study presents an enhanced training method using the Adaboost algorithm which is capable of obtaining the localized sampling optimum (LSO) from a local IP-CAM video. In addition, we use an improved motion detection algorithm that cooperates with the former face detector to speed up processing time and achieve a better detection rate on video-rate processing speed. The proposed solution has been developed around the cascaded AdaBoost approach, using the open-CV library, with a LSO from a local IP-CAM video. An efficient motion detection model is adopted for practical applications. The overall system performance using 30% local samples can be improved to a 97.9% detection rate and reduce detection time by 54.5% with regard to the Alt2 cascade.

Multi-sector algorithm for hardware acceleration of the general Hough transform

The Multi-Sector Algorithm (MSA) is a simplification of the CORDIC algorithm to more closely meet the requirements for real-time general Hough transform applications. The MSA can form a pipeline, and multiple angle rotations are performed in parallel. The whole has been tested on Virtex platform FPGAs to find straight edges within images. Angular resolution is incrementally scalable. Video-rate processing is easily achieved. The ability to run independent MS units in parallel is only limited by on-chip memory restrictions.

Reconfigurable hardware implementation of a phase-correlation stereoalgorithm

This paper describes the implementation of a stereo-vision system using Field Programmable Gate Arrays (FPGAs). Reconfigurable hardware, including FPGAs, is an attractive platform for implementing vision algorithms due to its ability to exploit parallelism often found in these algorithms, and due to the speed with which applications can be developed as compared to hardware. The system outputs 8-bit, subpixel disparity estimates for 256× 360 pixel images at 30,fps. A local-weighted phase correlation algorithm for stereo disparity [Fleet, D. J.: {Int. Conf. Syst. Man Cybernetics 1:48–54 (1994)] is implemented. Despite the complexity of performing correlations on multiscale, multiorientation phase data, the system runs as much as 300 times faster in hardware than its software implementation. This paper describes the hardware platform used, the algorithm, and the issues encountered during its hardware implementation. Of particular interest is the implementation of multiscale, steerable filters, which are widely used in computer vision algorithms. Several trade-offs (reducing the number of filter orientations from three to two, using fixed-point computation, changing the location of one localized low-pass filter, and using L1 instead of L2 norms) were required to both fit the design into the available hardware and to achieve video-rate processing. Finally, results from the system are given both for synthetic data sets as well as several standard stereo-pair test images.

An Approach to the Urban Scene Understanding Problem Useful for Autonomous Navigation

This paper presents an approach to the urban scene understanding problem, providing a robust expert system able to take out natural elements such as trees or plants. The system is based on a wide range of natural features associated to seasons, weather, chromatic components, sunshine levels, etc. A particularity of the system is that it is only dealing with pixels, so video-rate processing can be achieved in an easy way, whereas others which deal with regions. Then, the proposed expert system works as a pre-processor and needs, indeed, knowledgement about the environment. Although, pixels candidates could be associated to regions in order to be useful for a further high level processing. In this sense, the system would be applied to a mobile robot in order to use the trees as landmarks for navigation.

Sensory selection in vehicle detection and avoidance

A general paradigm for vehicle detection and avoidance by proper selection of visual and sonar sensors is presented. The most appropriate sensor for detection and navigation of the robot is selected in accordance with the sensor functions and limitations. This strategy is activated when one sensor cannot obtain enough information for navigation of the robot because of sensor limitations. Five types of actions based on stereotyped motion are used for the navigation system: Moving Along Wall, Moving Along, Moving Toward, Tracking Motion and Danger Estimation. The first is sonar based and the rest are vision based actions. Visual detection of the vehicle is based on the locomotion strategy “Sign Pattern based Stereotyped Motion” . The sign pattern of the vehicle is the shadow underneath the vehicle, which is darker than any other parts of the paved road. The robot detects the sign pattern of a vehicle from a distance of more than 30 m and extracts its front or rear shape on 2-D image by video rate processing. Moreover, to make a decision for further action of the robot, a time series information of vehicles on the paved road are provided during tracking process.

The microcomputer and image analysis in diagnostic pathology.

This paper presents a snapshot view of the influence and direction of microcomputer technology for image analysis techniques in diagnostic pathology. Microcomputers have had considerable impact in bringing image analysis to wider application. Semi-automated tracing techniques are a simple means of providing objective data and assist in a wide range of diagnostic problems. From the common theme of reducing subjectivity in diagnostic assessment, an extensive body of research has accrued. Some studies have addressed the need for quality control for reliable, routine application. Video digitizer cards bring digital image analysis within the reach of laboratory budgets, providing powerful tools for investigation of a wide range of cellular and tissue features. The use of staining procedures compatible with quantitative evaluation has become equally important. As well as assisting scene segmentation, cytochemical and immunochemical staining techniques relate the data to biological processes. With the present state of the art, practical use of microcomputer based image analysis is impaired by limitations of information extraction and specimen throughput. Recent advances in colour video imaging provide an extra dimension in the analysis of multi-spectral stains. Improvements will also be felt with predictable increase in speed of microprocessors, and with single chip devices which deliver video rate processing. If the full potential of this hardware is realized, high-speed, routine analysis becomes feasible. In addition, a microcomputer imaging system can play host to companion functions, such as image archiving and transmission. With this outlook, the use of microcomputers for image analysis in diagnostic pathology is certain to increase.(ABSTRACT TRUNCATED AT 250 WORDS)

Video-rate digital image analysis equipment

In parallel cellular arrays the same instruction may be executed on many pixels in parallel. Some commercially available systems use an alternative approach in which the same instruction is executed on many pixels serially, at approximately 10 7 pixels s −1: this is known as video-rate processing. Besides table look-up and arithmetical operations, ambitious connectivity-based image analysis is performed at video rates in commercially available equipment. For example, a histogram showing how many separate connected regions have what area can be obtained in one video frame time. This paper reviews various video-rate techniques, and proposes a microprocessor technique for video-rate connectivity-based analysis. Graphics capabilities such as roam and movie are not reviewed.