Using template matching for object recognition in infrared video sequences

The emerging standard of High Efficiency Video Coding (HEVC) provides a 50% improved compression performance compared to its predecessor H.264/AVC at the expense of increasing its computational complexity which is due to a large number of modes involved in the decision process where it would increase encoding time and provide hardware limitations. In this paper, the reduction of intra-coding complexity is proposed by utilization of Rate-Distortion Optimization (RDO) in preselecting a mode with the best RD cost, among all 35 intra-modes. Two cost functions – Sum of Absolute Difference (SAD) and Sum of Absolute Transform Difference (SATD, available in the HEVC Test Model (HM) Reference Software, are determined by making encoder decisions. This paper compares the performance and complexity cost of SAD only for intra-mode, with SATD-based intra-mode by modifying the HM reference encoder through forced selection of the mentioned modes. Results show that SAD consistently produces the least encoding time among all modes, along with sensible values of bitrate. Furthermore, error concealment was introduced in decoding the video sequences with the use of IEEE 802.22 Standard which only allowed power gains resulting to packet error rates (PER) ranging from 1% to 30% for the analysis on the behavior of each video sequence in an environment where error is introduced.

In digital image processing, template matching is a process to determine the location of sub image inside an image. The sub image, which is called template, usually has similarity with a part of the image. The template can be in different size, color or form. Template matching is famously used in image registration and object recognition. In this paper, we focus on the performance of the Sum of Squared Differences (SSD) and Normalized Cross Correlation (NCC)as the techniques that used in image registration for matching the template with an image. This experiment is aiming to compare the ability of both techniques in term of quality of output image as well as the time taken in execution process. Furthermore, it also to test the effect of template image to output image when there is noise and rotation. This paper provides an explanation about the concept of similarity measure techniques and how the algorithms are implementing in image registration process. Finally, the performance of these methods is tested by making comparison based on the value of correlation coefficient that produced from different image templates.

In many image processing applications, the Template Matching (TM) technique plays an important role in recognizing and locating patterns or objects within a digital image. The main task of the TM is to seeks and find a position within an original image that resembles a predetermined sub-image (template) and a corresponding region of the original image as much as possible. TM involves two main aspects: similarity measurement and search strategy. The simplest method applied to TM involves a comprehensive calculation of the value of the Normalized Cross-Correlation (NCC) over all the pixel locations of the source image (search strategy). Unfortunately, the high computational cost that implies the evaluation of the NCC coefficient makes this approach restricted. We propose several TM methods based on evolutionary approaches as an alternative to reduce the number of search locations in the TM process. We have conducted a comparison of several evolutionary methods, to obtain which of these is the optimum to perform the TM task. Experimental results of this comparison show us which methods achieve the best balance between estimation and computational cost.

The traditional global template matching is time consuming, has low accuracy, and cannot be adapted to rotation and scale change. The template matching technique proposed in this study improves the time, accuracy and robustness for printed circuit boards (PCB). In order to shorten the image positioning time, the image preprocessing is implemented on PCB image and the image blocks are labeled to obtain the tagged image, and the feature vector is extracted and the marking point region image is selected. The feature vector with rotation change and scale change robustness is extracted from the tagged image after labeling in the PCB image by using artificial neural network, combined with image moments for training. The marking point region image in the PCB image is selected. The scale value of the marking point region image is estimated by parametric template vector matching. The deflection angle of marking point region image is calculated by Hough transform. The obtained scale value and deflection angle value are used for fast template matching to determine the marking point positioning. The three-dimensional (3D) parabolic curve fitting is implemented in marking point positioning and adjacent pixel position to reach the sub-pixel level accuracy. The experiment showed that the proposed template matching technique for the PCB image with or without noise or angle rotation, the average position accuracy error of each translated image is lower than 7 \(\upmu \)m, and the error standard deviation is lower than 5 \(\upmu \)m. The rotation angle error average and standard deviation of angular error of Hough transform are lower than 0.2\(^{\circ }\), more accurate than orientation code (OC) method. The scale value estimation, relative error average and error standard deviation are lower than 0.004 and 0.006 for the image with or without noise. The average complete positioning time of PCB image at resolution of \(2500\times 2500\) is only 0.55 s, which is better than the 3.97 s of traditional global template matching. The results prove that the template matching technique of this study not only has sub-pixel level high accuracy and short computing time, but also has the robustness of rotation change and scale change interference. It can implement rapid, efficient and accurate positioning.

Abstract
 This research was conducted to determine the accuracy of the Sum of Squared Difference (SSD) Template Matching method in the Application of Learning Numbers Writing Games. This game application is an application created to help early childhood in recognizing Arabic numbers, namely numbers from 0 to 9. In the SSD Template Matching method there are several processes including Preprocessing, thinning, feature extraction, and classification (SSD template matching). In testing the game application involves 10 respondents who were asked to write numbers correctly as requested by the application. For each number writing test, it is tested by 3 times. From the tests conducted, obtained an accuracy of 94.67%.
 Keyword: Template Matching, Sum of Squared Difference (SSD), Education Game, Optical Character Recognition, Mobile Learning

As oil palm is cultivated in large-scale plantations, prior and post-planting operations are laborious and time expensive, and also manual implementation of some of these operations often results in incorrect measurements and information. Successful oil palm management in prior and post-planting operations requires effective techniques to collect precise information. Unmanned aerial vehicle (UAV) imagery is a low-cost alternative to field-based assessment but requires the development of methods to easily and accurately extract the required information. The individual oil palm tree detection and height assessment are important and labor-intensive tasks for large-scale plantations where trees taller than 15 m are being replanted due to the high cost of harvesting and low yield. Therefore, in this chapter we demonstrate a general work flow for individual oil palm detection and height assessment using UAV imagery. We explain local maximum (LM) and template matching (TM) techniques as two commonly used approaches in individual tree detection. The accuracy of each method was evaluated on 20 randomly selected plots on UAV image with recall, precision, and F-score method. The F-score for LM method is higher than TM methods which, respectively, are 0.83 and 0.60. From 17,252 oil palm trees in the 20 plots, LM algorithm could detect 1395 (almost 80%) and TM algorithm, 967 (almost 55%). Three hundred fifty-seven and 785 trees have been missed, respectively, in LM and TM approaches. In both cases, background vegetation incorrectly has been labeled as oil palm tree, where 141 and 322 objects have been falsely detected as oil palm tree in LM and TM approaches. LM worked better in almost all of the plots; however the performance decreased in highly dense area. Contradictory to TM approach, in LM approach, shadows did not affect the performance as it was reflected in precision value. In densely cultivated plots due to leaves overlapping of neighboring trees, algorithm failed, and also in sparsely cultivated plots, shadows caused some commission errors. Inherited distortion of UAV image also caused some omission errors in TM approach. Individual detected tree with LM algorithm was used in the next part for oil palm height estimation overlaying with canopy height model.

Purpose – Mobile robots become more and more important for many potential applications such as navigation and surveillance. The paper proposes an image processing scheme for moving object detection from a mobile robot with a single camera. It especially aims at intruder detection for the security robot on either smooth paved surfaces or uneven ground surfaces. Design/methodology/approach – The core of the proposed scheme is the template matching with basis image reconstruction for the alignment between two consecutive images in the video sequence. The most representative template patches in one image are first automatically selected based on the gradient energies in the patches. The chosen templates then form a basis matrix, and the instances of the templates in the subsequent image are matched by evaluating their reconstruction error from the basis matrix. For the two well-aligned images, a simple and fast temporal difference can thus be applied to identify moving objects from the background. Findings – The proposed template matching can tolerate in rotation (±10°) and (±10°) in scaling. By adding templates with larger rotational angles in the basis matrixes, the proposed method can be further extended for the match of images from severe camera vibrations. Experimental results of video sequences from a non-stationary camera have shown that the proposed scheme can reliably detect moving objects from the scenes with either minor or severe geometric transformation changes. The proposed scheme can achieve a fast processing rate of 32 frames per second for an image of size 160×120. Originality/value – The basic approaches for moving object detection with a mobile robot are feature-point match and optical flow. They are relatively computational intensive and complicated to implement for real-time applications. The proposed template selection and template matching are very fast and easy to implement. Traditional template matching methods are based on sum of squared differences or normalized cross correlation. They are very sensitive to minor displacement between two images. The proposed new similarity measure is based on the reconstruction error from the test image and its reconstruction from the linear combination of the templates. It is thus robust under rotation and scale changes. It can be well suited for mobile robot surveillance.

For many image processing applications (such as feature tracking, object recognition, stereo matching and remote sensing), the technique known as Template Matching (TM) plays an important role for the localization and recognition of objects or patterns within a digital image. A TM approach seeks to find a position within a source image which yields to the best possible resemblance between a given sub-image (typically referred as image template) and a corresponding region of such source image. TM involves two critical aspects: similarity measurement and search strategy. In this sense, the simplest available TM method involves an exhaustive computation of the Normalized Cross-Correlation (NCC) value (similarity measurement) over all pixel locations of the source image (search strategy). Unfortunately, this approach is strongly restricted due to the high computational cost implied in the evaluation of the NCC coefficient. Recently, several TM methods based on evolutionary approaches have been proposed as an alternative to reduce the number of search locations in the TM process. However, the lack of balance between exploration and exploitation related to the operators employed by many of such approaches makes TM to suffer from several critical flaws, such as premature convergence. In the proposed approach, the swarm optimization method known as Locust Search (LS) is applied to solve the problem of template matching. The unique evolutionary operators employed by LS method’s search strategy allows to explicitly avoid the concentration of search agents toward the best-known solutions, which in turn allows a better exploration of the valid image’s search region. Experimental results show that, in comparison to other similar methods, the proposed approach achieves the best balance between estimation accuracy and computational cost.

This paper presents a technique for high-accuracy correspondence search between two rectified images using 1D phase-only correlation (POC). The correspondence search between stereo images can be reduced to 1D search through image rectification. However, we usually employ block matching with 2D rectangular image blocks for finding the best matching point in the 1D search. We propose the use of 1D POC (instead of 2D block matching) for stereo correspondence search. The use of 1D POC makes possible significant reduction in computational cost without sacrificing reconstruction accuracy compared with the 2D POC-based approach. Also, the resulting reconstruction accuracy is much higher than those of conventional stereo matching techniques using SAD (sum of absolute differences) and SSD (sum of squared differences) combined with sub-pixel disparity estimation.

As the industry's leading mobile GPU, and one of the earliest OpenCL™ adopters, Adreno™ in Qualcomm®'s Snapdragon™ SOCs has been supporting OpenCL since its A3x family, throughout A4x and A5x and the latest A6x family.

The growing popularity of high resolution video and the continuously increasing demands for high quality video on mobile devices are producing stronger needs for more efficient video encoder. Concerning these desires, HEVC, a newest video coding standard, has been developed by a joint team formed by ISO/IEO MPEG and ITU/T VCEG. Its design goal is to achieve a 50% compression gain over its predecessor H.264 with an equal or even higher perceptual video quality. Motion Estimation (ME) being as one of the most critical module in video coding contributes almost 50%-70% of computational complexity in the video encoder. This high consumption of the computational resources puts a limit on the performance of encoders, especially for full HD or ultra HD videos, in terms of coding speed, bit-rate and video quality. Thus the major part of this work concentrates on the computational complexity reduction and improvement of timing performance of motion estimation algorithms for HEVC standard. First, a new strategy to calculate the SAD (Sum of Absolute Difference) for motion estimation is designed based on the statistics on property of pixel data of video sequences. This statistics demonstrates the size relationship between the sum of two sets of pixels has a determined connection with the distribution of the size relationship between individual pixels from the two sets. Taking the advantage of this observation, only a small proportion of pixels is necessary to be involved in the SAD calculation. Simulations show that the amount of computations required in the full search algorithm is reduced by about 58% on average and up to 70% in the best case. Secondly, from the scope of parallelization an enhanced TZ search for HEVC is proposed using novel schemes of multiple MVPs (motion vector predictor) and shared MVP. Specifically, resorting to multiple MVPs the initial search process is performed in parallel at multiple search centers, and the ME processing engine for PUs within one CU are parallelized based on the MVP sharing scheme on CU (coding unit) level. Moreover, the SAD module for ME engine is also parallelly implemented for PU size of 32×32. Experiments indicate it achieves an appreciable improvement on the throughput and coding efficiency of the HEVC video encoder. In addition, the other part of this thesis is contributed to the VLSI architecture design for finding the first W maximum/minimum values targeting towards high speed and low hardware cost. The architecture based on the novel bit-wise AND scheme has only half of the area of the best reference solution and its critical path delay is comparable with other implementations. While the FPCG (full parallel comparison grid) architecture, which utilizes the optimized comparator-based structure, achieves 3.6 times faster on average on the speed and even 5.2 times faster at best comparing with the reference architectures. Finally the architecture using the partial sorting strategy reaches a good balance on the timing performance and area, which has a slightly lower or comparable speed with FPCG architecture and a acceptable hardware cost

In Motion estimation (ME), the block matching algorithms have a great potential of parallelism. This process of the best match is performed by computing the similarity for each block position inside the search area, using a similarity metric, such as Sum of Absolute Differences (SAD). It is used in the various steps of motion estimation algorithms. Moreover, it can be parallelized using Graphics Processing Unit (GPU) since the computation algorithm of each block pixels is similar, thus offering better results. In this work a fixed OpenCL code was performed firstly on several architectures as CPU and GPU, secondly a parallel GPU-implementation was proposed with CUDA and OpenCL for the SAD process using block of sizes from 4x4 to 64x64. A comparative study established between execution time on GPU on the same video sequence. The experimental results indicated that GPU OpenCL execution time was better than that of CUDA times with performance ratio that reached the double.

The technique of template matching in the log-polar visibility (magnitude of Fourier transform in the logarithmic radius and azimuth plane) is proposed as a promising tool for many problems of isolated object recognition irrespective of its position, scale, and rotation. The properties of the log-polar visibility suggests the use of partial information to implement some forms of "reduced template matching". These techniques imply substantial reduction in the computational cost.

This paper compares the performance of various spectral shift estimators for use in spectral elastography, namely, the normalized cross-correlation (NCC), sum squared difference (SSD), and sum absolute difference (SAD). Simulation results demonstrate that the spectral SSD-based elastographic method exhibits no marked difference in performance compared to the more computationally costly NCC-based approach, which has to date been the preferred estimator in spectral elastography. The spectral SAD-based strain estimator, though computationally less burdening, failed to outperform the NCC- and SSD-based techniques. Furthermore, though spectral subsample estimation techniques using a cosine-fit interpolation method outperformed that of the parabolic-fit method in terms of both reduced bias errors and standard deviations, the latter was selected in this study due to computational simplicity. The role of spectral density was evaluated without and with parabolic-based subsample interpolation. Based on minimizing computational complexity, it is concluded that a (low density) spectral SSD strain estimator coupled with parabolic-based subsample estimation is the preferred choice for spectral elastography. Keywords-elasticity imaging; spectral elastography; strain filter; subsample estimation; ultrasound imaging

Template matching is used for many applications in image processing. Cross Correlation is the basic statistical approach to image registration. It is used for template matching or pattern recognition. Template can be considered a sub-image from the reference image, and the image can be considered as a sensed image. The objective is to establish the correspondence between the reference image and sensed image. It gives the measure of the degree of similarity between an image and template. This paper describes medical image registration by template matching based on Normalized Cross-Correlation (NCC) using Cauchy-Schwartz inequality. The algorithm for template matching using NCC is implemented in MATLAB. The algorithm does the template matching and uses the Cauchy-Schwartz’s inequality to simplify the procedure. The developed algorithm is robust for similarity measure. An experimental result with medical images registration with noise and without noise is shown in the results section.