• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.4
• /
• pp.212-222
• /
• 2003

The ability to efficiently and robustly recover accurate 3D terrain models from sets of stereoscopic images is important to many civilian and military applications. A stereo matching has been an important tool for reconstructing three dimensional terrain. However, there exist many factors causing stereo matching error, such as occlusion, no feature or repetitive pattern in the correlation window, intensity variation, etc. Among them, occlusion can be only resolved by true multi-image stereo. In this paper, we present multi-image stereo method using DEM fusion as one of efficient and reliable true multi-image methods. Elevations generated by all pairs of images are combined by the fusion process which accepts an accurate elevation and rejects an outlier. We propose three fusion schemes: THD(Thresholding), BPS(Best Pair Selection) and MS(Median Selection). THD averages elevations after rejecting outliers by thresholding, while BPS selects the most reliable elevation. To determine the reliability of a elevation or detect the outlier, we employ the measure of self-consistency. The last scheme, MS, selects the median value of elevations. We test the effectiveness of the proposed methods with a quantitative analysis using simulated images. Experimental results indicate that all three fusion schemes showed much better improvement over the conventional binocular stereo in natural terrain of 29 Palms and urban site of Avenches.

• The KIPS Transactions:PartB
• /
• v.17B no.2
• /
• pp.115-124
• /
• 2010

Stereo matching techniques are categorized in two major schemes, local and global matching techniques. In global matching schemes, several investigations are introduced, where cost accumulation is performed in multiple matching lines. In this paper, we introduce a new multi-line stereo matching techniques which expands a conventional single-line matching scheme to multiple one. Matching cost is based on simple normalized cross correlation. We expand the scan-line optimization technique to a multi-line scan-line optimization technique. The proposed technique first generates a reliability image, which is iteratively updated based on the previous reliability measure. After some number of iterations, the reliability image is completed by a hole-filling algorithm. The hole-filling algorithm introduces a disparity score table which records the disparity score of the current pixel. The disparity of an empty pixel is determined by comparing the scores of the neighboring pixels. The proposed technique is tested using the Middlebury and CMU stereo images. The error analysis shows that the proposed matching technique yields better performance than using conventional global matching algorithm.

• Journal of Mechanical Science and Technology
• /
• v.17 no.10
• /
• pp.1411-1422
• /
• 2003

The detection of free spaces between obstacles in a scene is a prerequisite for navigation of a mobile robot. Especially for stereo vision-based navigation, the problem of correspondence between two images is well known to be of crucial importance. This paper describes multi-range approach of area-based stereo matching for grid mapping and visual navigation in uncertain environment. Camera calibration parameters are optimized by evolutionary algorithm for successful stereo matching. To obtain reliable disparity information from both images, stereo images are to be decomposed into three pairs of images with different resolution based on measurement of disparities. The advantage of multi-range approach is that we can get more reliable disparity in each defined range because disparities from high resolution image are used for farther object a while disparities from low resolution images are used for close objects. The reliable disparity map is combined through post-processing for rejecting incorrect disparity information from each disparity map. The real distance from a disparity image is converted into an occupancy grid representation of a mobile robot. We have investigated the possibility of multi-range approach for the detection of obstacles and visual mapping through various experiments.

• Korean Journal of Geomatics
• /
• v.1 no.1
• /
• pp.43-49
• /
• 2001

Although many kinds of stereo matching method have been developed in the field of computer vision and photogrammetry, wrong matches are not easy to avoid. This paper presents a new method to reduce wrong matches after matching, and experimental results are reported. The main idea is to analyze the histogram of the image attribute differences between each pair of image patches matched. Typical image attributes of image patch are the mean and the standard deviation of gray value for each image patch, but there could be other kinds of image attributes. Another idea is to check relative position among potential matches. This paper proposes to use Gaussian blunder filter to detect the suspicious pair of candidate match in relative position among neighboring candidate matches. If the suspicious candidate matches in image attribute difference or relative position are suppressed, then many wrong matches are removed, but minimizing the suppression of good matches. The proposed method is easy to implement, and also has potential to be applied as post processing after image matching for many kinds of matching methods such as area based matching, feature matching, relaxation matching, dynamic programming, and multi-channel image matching. Results show that the proposed method produces fewer wrong matches than before.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2295-2298
• /
• 2003

The correspondence problem for stereo image matching plays an important role in expanding view points as multi view video applications become more popular. The conventional disparity estimation algorithms have limitation to find exact disparities because they consider not image features but similiar intensity points. Thus we propose an efficient disparity estimation algorithm considering features of stereo image pairs. As simulation results, our proposed method confirms better intermediate views than the existing block-matching methods.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.1
• /
• pp.12-18
• /
• 2012

Stereo correspondence is the central problem of stereo vision. In this paper, we propose a stereo matching scheme based on a genetic algorithm using a multi-resolution method and AD-Census. The proposed approach considers the matching environment as an optimization problem and finds the disparity by using a genetic algorithm And adaptive chronosome structure using edge pixels and crossover mechanism are employed in this technique. A cost function is composes of certain constraints whice are commonly used in stereo matching. AD-Census measure is applied to reduce disparity error. To increase the efficiency of process, we apply image pyramid method to stereo matching and calculate the initial disparity map at the coarsest resolution. Then initial disparity map is propagated to the next finer resolution, interpolated and performed disparity refinement using local feature vector. We valid our method not only reduces the search time for correspondence compared with conventional GA-based method but also ensures the validity of matching.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.6
• /
• pp.3208-3229
• /
• 2017

Rectification is an essential procedure for simplifying the disparity extraction of stereo matching algorithms by removing vertical mismatches between left and right images. To support real-time stereo matching, studies have introduced several look-up table (LUT)- and computational logic (CL)-based rectification approaches. However, to support high-resolution images, the LUT-based approach requires considerable memory resources, and the CL-based approach requires numerous hardware resources for its circuit implementation. Thus, this paper proposes a multi-level accumulation-based rectification method as a simple CL-based method and its circuit implementation. The proposed method, which includes distortion correction, reduces addition operations by 29%, and removes multiplication operations by replacing the complex matrix computations and high-degree polynomial calculations of the conventional rectification with simple multi-level accumulations. The proposed rectification circuit can rectify $1,280{\times}720$ stereo images at a frame rate of 135 fps at a clock frequency of 125 MHz. Because the circuit is fully pipelined, it continuously generates a pair of left and right rectified pixels every cycle after 13-cycle latency plus initial image buffering time. Experimental results show that the proposed method requires significantly fewer hardware resources than the conventional method while the differences between the results of the proposed and conventional full rectifications are negligible.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.5
• /
• pp.179-186
• /
• 2021

For stereo matching based on deep learning, the design of network structure is crucial to the calculation of matching cost, and the time-consuming problem of convolutional neural network in image processing also needs to be solved urgently. In this paper, a method of stereo matching using sparse loss volume in parallax dimension is proposed. A sparse 3D loss volume is constructed by using a wide step length translation of the right view feature map, which reduces the video memory and computing resources required by the 3D convolution module by several times. In order to improve the accuracy of the algorithm, the nonlinear up-sampling of the matching loss in the parallax dimension is carried out by using the method of multi-category output, and the training model is combined with two kinds of loss functions. Compared with the benchmark algorithm, the proposed algorithm not only improves the accuracy but also shortens the running time by about 30%.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.11
• /
• pp.899-905
• /
• 2003

An intermediate images generation method using multi-resolution based hierarchical block matching disparity map is proposed. This method is composed of a disparity estimation, an occlusion detection and intermediate image synthesis. For the disparity estimation, which is one of the important processes in intermediate image synthesis, we use the multi-resolution based hierarchical block matching algorithm to overcome the imperfect ness of block matching algorithm. The proposed method makes disparity maps more accurate and dense by multi-resolution based hierarchical block matching, and the estimated disparity maps are used to generate intermediate images of stereo images. Generated intermediate images show 0.1∼1.4 ㏈ higher PSNR than the images obtained by block matching algorithm.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.4
• /
• pp.277-285
• /
• 2004

We present a new hybrid stereo matching technique in terms of the co-operation of area-based stereo and feature-based stereo. The core of our technique is that feature matching is carried out by the reference of the disparity evaluated by area-based stereo. Since the reference of the disparity can significantly reduce the number of feature matching combinations, feature matching error can be drastically minimized. One requirement of the disparity to be referenced is that it should be reliable to be used in feature matching. To measure the reliability of the disparity, in this paper, we employ the self-consistency of the disunity Our suggested technique is applied to the detection of 3D line segments by 2D line matching using our hybrid stereo matching, which can be efficiently utilized in the generation of the rooftop model from urban imagery. We carry out the experiments on our hybrid stereo matching scheme. We generate synthetic images by photo-realistic simulation on Avenches data set of Ascona aerial images. Experimental results indicate that the extracted 3D line segments have an average error of 0.5m and verify our proposed scheme. In order to apply our method to the generation of 3D model in urban imagery, we carry out Preliminary experiments for rooftop generation. Since occlusions are occurred around the outlines of buildings, we experimentally suggested multi-image hybrid stereo system, based on the fusion of 3D line segments. In terms of the simple domain-specific 3D grouping scheme, we notice that an accurate 3D rooftop model can be generated. In this context, we expect that an extended 3D grouping scheme using our hybrid technique can be efficiently applied to the construction of 3D models with more general types of building rooftops.