Visual surveillance for traffic systems requires short processing time, low processing cost and high reliability. Under
those requirements, image processing technologies offer a variety of systems and methods for Intelligence
Transportation Systems (ITS) as a platform for traffic Automatic Incident Detection (AID). There exist two classes of
AID methods mainly studied: one is based on inductive loops, radars, infrared sonar and microwave detectors and the
other is based on video images. The first class of methods suffers from drawbacks in that they are expensive to install
and maintain and they are unable to detect slow or stationary vehicles. Video sensors, on the other hand, offer a
relatively low installation cost with little traffic disruption during maintenance. Furthermore, they provide wide area
monitoring allowing analysis of traffic flows and turning movements, speed measurement, multiple-point vehicle counts,
vehicle classification and highway state assessment, based on precise scene motion analysis.
This paper suggests the utilization of traffic models for real-time vision-based traffic analysis and automatic incident
detection. First, the traffic flow variables, are introduced. Then, it is described how those variables can be measured from
traffic video streams in real-time. Having the traffic variables measured, a robust automatic incident detection scheme is
suggested. The results presented here, show a great potential for integration of traffic flow models into video based
intelligent transportation systems. The system real time performance is achieved by utilizing multi-core technology using
standard parallelization algorithms and libraries (OpenMP, IPP).
One of the key aspects of 3D visualization is computation of depth maps. Depth maps enables synthesis of 3D video
from 2D video and use of multi-view displays. Depth maps can be acquired in several ways. One method is to measure
the real 3D properties of the scene objects. Other methods rely on using two cameras and computing the correspondence
for each pixel. Once a depth map is acquired for every frame, it can be used to construct its artificial stereo pair.
There are many known methods for computing the optical flow between adjacent video frames. The drawback of these
methods is that they require extensive computation power and are not very well suited to high quality real-time 3D
rendering. One efficient method for computing depth maps is extraction of motion vector information from standard
video encoders. In this paper we present methods to improve the 3D visualization quality acquired from compression
CODECS by spatial/temporal and logical operations and manipulations.
We show how an efficient real time implementation of spatial-temporal local order statistics such as median and local
adaptive filtering in 3D-DCT domain can substantially improve the quality of depth maps and consequently 3D video
while retaining real-time rendering.
Real-time performance is achived by utilizing multi-core technology using standard parallelization algorithms and
libraries (OpenMP, IPP).
Optical flow algorithms for estimating image local motion in video sequences are based on the first term Taylor series
expansion approximation of image variations caused by motion, which requires computing image spatial derivatives. In
this paper we report an analytical assessment of lower bounds of optical flow estimation errors defined by the accuracy
of the Taylor series expansion approximation of image variations and results of experimental comparison of performance
of known optical flow methods, in which image differentiation was implemented through different commonly used
numerical differentiation methods and through DFT/DCT based algorithms for precise differentiation of sampled data.
The comparison tests were carried out using simulated sequences as well as real-life image sequences commonly used
for comparison of optical flow methods. The simulated sequences were generated using, as test images, pseudo-random
images with uniform spectrum within a certain fraction of the image base band specified by the image sampling rate, the
fraction being a parameter specifying frequency contents of test images. The experiments have shown that performance
of the optical flow methods can be significantly improved compared to the commonly used numerical differentiation
methods by using the DFT/ DCT-based differentiation algorithms especially for images with substantial high-frequency
A common distortion in videos acquired in long range observation systems is image instability in form of chaotic local
displacements of image frames caused by fluctuations in the refraction index of the atmosphere turbulence. At the same
time, such videos, which are designed to present moving objects on a stable background, contain tremendous
redundancy that potentially can be used for image stabilization and perfecting provided reliable separation of stable
background from true moving objects. Recently, it was proposed to use this redundancy for resolution enhancement of
turbulent video through elastic registration, with sub-pixel accuracy, of segments of video frames that represent stable
scenes. This paper presents results of investigation, by means of computer simulation, into how parameters of such a
resolution enhancement process affect its performance and its potentials and limitations.
It has been shown that one can make use of local instabilities in turbulent video frames to enhance image resolution
beyond the limit defined by the image sampling rate. This paper outlines a real-time solution for the implementation of
super-resolution algorithm on MPEG-4 platforms. The MPEG-4 video compression standard offer, in real-time, several
features, such as motion extraction with quarter pixel accuracy, scene segmentation to video object planes, global motion
compensation and de-blocking and de-ringing filters, which can be incorporated into the super-resolution process to
produce enhanced visual output. Experimental verification on real-life videos is also provided.
In this paper we present experimental evidence of the redundancy of depth maps for 3D visualization. To this end, we performed a series of statistical experiments, devised to measure the effect of depth map quantization and the resolving power of 3D perception. The results of these tests show that for good 3D perception and 3D visualization, one does not need to use depth map of the same resolution neither with the same quantization as the original images. These results indicate that depth map based visualization can be based on low resolution, coarsely quantized, depth maps without significant degradation in the perceived 3D image.
Image evaluation and quality measurements are fundamental components in all image processing applications and
techniques. Recently, a no-reference perceptual blur metrics (PBM) was suggested for numerical evaluation of blur
effects. The method is based on computing the intensity variations between neighboring pixels of the input image
before and after low-pass filtering. The method was proved to demonstrate a very good correlation between the
quantitative measure it provides and visual evaluation of perceptual image quality. However, this quantitative image
blurriness measure has no intuitive meaning and has no association with conventionally accepted imaging system design
parameters such as, for instance, image bandwidth.
In this paper, we suggest an extended modification of this PBM-method that provides such a direct association and
allows evaluation image in terms of the image efficient bandwidth. To this end we apply the PBM-method to a series of
test pseudo-random images with uniform spectrum of different spread within the image base-band defined by the image
sampling rate and map the image blur measurement results obtained for this set of test images to corresponding
measures of their bandwidths. In this way we obtain a new image feature, which provides evaluation of image in terms
of the image effective bandwidth measured in fractions, from 0 to 1, of the image base-band. In addition, we also show
that the effective bandwidth measure provides a good estimation for the potential JPEG encoder compression rate,
which allows one to choose the best compression quality for a requested compressed image size.
In this paper, we present an efficient method to synthesize 3D video from compressed 2D video. The 2D video is
analyzed by computing frame-by-frame motion maps. For this computation, MPEG motion vectors extraction was
performed. Using the extracted motion vector maps, the video undergoes analysis and the frames are segmented to
provide object-wise depth ordering. The frames are then used to synthesize stereo pairs. This is performed by
resampling the video frames on a grid that is governed by a corresponding depth-map. In order to improve the quality of
the synthetic video, as well as to enable 2D viewing where 3D visualization is not possible, several techniques for image
enhancement are used. In our test case, anaglyph projection was selected as the 3D visualization method, as the method
is mostly suited to standard displays. The drawback of this method is ghosting artifacts. In our implementation we
minimize these unwanted artifacts by modifying the computed depth-maps using non-linear transformations.
Defocusing of one anaglyph color component was also used to counter such artifacts. Our results show that the
suggested methods enable synthesis of high quality 3D videos in real-time.
Long Range Observation Systems is a domain, which carries a lot of interest in many fields such as astronomy (i.e.
planet exploration), geology, ecology, traffic control, remote sensing, and homeland security (surveillance and military
intelligence). Ideally, image quality would be limited only by the optical setup used, but, in such systems, the major
cause for image distortion is atmospheric turbulence. The paper presents a real-time algorithm that compensates images
distortion due to atmospheric turbulence in video sequences, while keeping the real moving objects in the video
unharmed. The algorithm is based on moving objects extraction; hence turbulence distortion compensation is applied
only to the static areas of images. For that purpose a hierarchical decision mechanism is suggested. First, a lightweight
computational decision mechanism which extracts most stationary areas is applied. Then a second step improves
accuracy by more computationally complex algorithms. Finally, all areas in the incoming frame that were tagged as
stationary are replaced with an estimation of the stationary scene. The restored videos exhibit excellent stability for
stationary objects while retaining real motion. This is achieved in real-time on standard computer hardware.
In this paper, we present methods to synthesize 3D video from arbitrary 2D video. The 2D video is analyzed by computing frame-by-frame motion maps. For this computation, several methods were tested, including optical flow, segmentation and correlation based target location. Using the computed motion maps, the video undergoes analysis and the frames are segmented to provide object-wise depth ordering. The frames are then used to synthesize stereo pairs. This is performed by resampling frames on a grid that is governed by a corresponding depth-map. In order to improve the quality of the synthetic video, as well as to enable 2D viewing where 3D visualization is not possible, several techniques for image enhancement are used. In our test case, anaglyph projection was selected as the 3D visualization method, as the method is mostly suited to standard displays. The drawback of this method is ghosting artifacts. In our implementation we minimize these unwanted artifacts by modifying the computed depth-maps using non-linear transformations. Defocusing of one anaglyph color component was also used to counter such artifacts. Our results show that the suggested methods enable synthesis of high quality 3D videos.