Improved Scale Invariant Feature Transform Algorithm Research Articles

Surround Sensing Technique for Trucks Based on Multi-Features and Improved Yolov5 Algorithm.

The traditional rearview mirror method cannot fully guarantee safety when driving trucks. RGB and infrared images collected by cameras are used for registration and recognition, so as to achieve the perception of surroundings and ensure safe driving. The traditional scale-invariant feature transform (SIFT) algorithm has a mismatching rate, and the YOLO algorithm has an optimization space in feature extraction. To address these issues, this paper proposes a truck surround sensing technique based on multi-features and an improved YOLOv5 algorithm. Firstly, the edge corner points and infrared features of the preset target region are extracted, and then a feature point set containing the improved SIFT algorithm is generated for registration. Finally, the YOLOv5 algorithm is improved by fusing infrared features and introducing a composite prediction mechanism at the prediction end. The simulation results show that, on average, the image stitching accuracy is improved by 17%, the time is reduced by 89%, and the target recognition accuracy is improved by 2.86%. The experimental results show that this method can effectively perceive the surroundings of trucks, accurately identify targets, and reduce the missed alarm rate and false alarm rate.

Application of Automatic Recognition and Positioning Technology of Industrial Robot based on Monocular Vision Technology in Vehicle Manufacturing

Combining machine vision technology with intelligent algorithms to improve the automatic identification and positioning technology of industrial robots to meet the production needs in different industrial environments is the current research direction of intelligent robots. In this study, an automatic identification and positioning technology for industrial robots based on monocular vision technology is proposed. First, the template matching algorithm and the Scale-invariant feature transform (SIFT) algorithm are introduced. Aiming at the shortcomings of the Hessian matrix in the SIFT algorithm in the process of eliminating boundary effects, an improved SIFT algorithm using Harris corner point detection is further proposed, and the improved SIFT algorithm is used in the automatic recognition and target positioning operations of industrial robots. In order to verify the performance of the proposed improved SIFT algorithm, the recognition accuracy and positioning angle deflection of the algorithm in different plastic sheets were detected. The experimental results show that under the improved SIFT algorithm, the recognition accuracy of five different styles of plastic sheets is above 98%. The improved SIFT algorithm also has less error between the predicted value and the actual value of the positioning angle deflection on the four plastic sheets. The robot under the improved algorithm is applied to the vehicle manufacturing industry and the production efficiency of the vehicle is improved through the automatic recognition and positioning technology of intelligent robot.

An improved SIFT algorithm for registration between SAR and optical images

Aiming at improving the performance of scale invariant feature transform (SIFT) algorithm during the registration of optical and synthetic aperture radar (SAR) images, a new SIFT algorithm is proposed. Firstly, the nonlinear diffusion scale space of optical and SAR images is constructed by using nonlinear diffusion filtering, the uniform gradient information is calculated by using multi-scale Sobel operator and multi-scale exponential weighted mean ratio operator respectively. Then, after removing the first layer of the scale space with the image blocking strategy, the scale space is partitioned, and Harris feature points are extracted on the basis of consistent gradient information to obtain stable and uniform point features. Descriptors are constructed based on gradient position and direction histogram templates and normalized to overcome nonlinear radiation differences between images. Finally, the correct matching point pairs are obtained by using bilateral fast approximate nearest neighbor (FLANN) search matching method and random sampling consistent (RANSAC) method, and the affine transformation model parameters are obtained. Compared with the other two algorithms, the CMR of this algorithm is improved by 80.53%, 75.61% and 81.74% respectively in the three groups of images, and the RMSE is reduced by 0.6491, 1.0287 and 0.6306 respectively.

Vibration detection method for core loosening degree of high‐voltage direct current converter valve saturable reactor based on variational mode decomposition‐symmetrized dot pattern and image matching

Saturable reactor is the key equipment in converter valves; it is important to evaluate the core condition. In this paper, a recognition model of saturable reactor core loosening based on variational mode decomposition (VMD)-symmetrized dot pattern (SDP) feature fusion images and scale-invariant feature transform (SIFT) was proposed. Firstly, the saturable reactor vibration test under high frequency pulse excitation was carried out, and the vibration signals in different core loosening degrees were collected. Secondly, the VMD algorithm was used to decompose the broadband vibration signal into multiple narrowband functions, which were used to reflect the characteristics of each frequency band. Thirdly, each function and the original signal were transformed by SDP, the generated spiral arms were fused into a new image, and the typical templates in different loosening degrees were selected. Finally, the improved SIFT algorithm was used to obtain the matching results between test sets and templates. The results show that the recognition accuracy of the proposed model for core loosening is 97.5%, which is better than traditional algorithms. It can find the core loosening defect early and avoid further failures such as water pipe break and discharge, which can provide an important basis for saturable reactor monitoring.

Multispectral image registration based on an improved scale-invariant feature transform algorithm

There are often significant intensity variations between multispectral images, making automatic registration tasks difficult. Traditional feature matching methods, such as the scale-invariant feature transform (SIFT), are often sensitive to nonlinear variations of intensity between multispectral images. To solve this problem, an improved SIFT algorithm is introduced. First, the contrast limited adaptive histogram equalization algorithm is introduced in the feature extraction stage to improve the feature point extraction results. Then, the Sobel operator is used to enhance the main direction consistency between homologous feature point pairs. The experimental results suggest that the method can obtain reliable registration results on unmanned aerial vehicle multispectral images.

Applying image registration algorithm combined with CNN model to video image stitching

The purposes are to explore the video image stitching technique of Unmanned Aerial Vehicles (UAVs), expand the application of image registration algorithms and new sensing equipment in video image stitching, and improve the development of video remote sensing image processing. First, how to remotely stitch UAV video images is analyzed. Second, the Scale Invariant Feature Transform (SIFT) algorithm is improved by re-dividing the pixel region and incorporating the vector correlation coefficient. Then, the matching results of the improved SIFT algorithm are compared with those of the traditional SIFT algorithm and Speed Up Robust Feature algorithm. Second, the Random Sample Consensus algorithm is introduced to match the video images accurately, and the matching accuracy of the converted images is verified. Finally, the improved image registration algorithm, the homography matrix estimation model based on convolutional neural network, and the conformation equation of the video sensor are combined to complete the video image stitching of UAVs. Also, the stitching quality of the video image is analyzed. The results show that the improved SIFT algorithm is better than the traditional SIFT algorithm in terms of correct matching and matching time. The visually transformed finely-matched image has a higher matching accuracy rate, and the combination of the two registration algorithms eliminates mismatch points effectively. Compared with the traditional stitching method, the video image stitching method proposed in this study has a higher structural similarity index and edge difference spectrum index, which is feasible and effective. The combination of image registration algorithm with new sensors and deep learning has great application potential in video image stitching.

An improved SIFT algorithm for robust emotion recognition under various face poses and illuminations

To address the variabilities of the number and position of extracted feature points for the traditional scale-invariant feature transform (SIFT) method, an improved SIFT algorithm is proposed for robust emotion recognition. Specifically, shape decomposition is first performed on the detected facial images by defining a weight vector. Then, a feature point constraint algorithm is developed to determine the optimum position of the feature points that can effectively represent the expression change regions. On this basis, the SIFT descriptors are applied to extract the regional gradient information as feature parameters. Finally, the support vector machine classifier combined with the principal component analysis method is used to reduce the feature dimensions and facial expression recognition. Experiments have been performed under different conditions, i.e., varied illuminations, face poses and facial moisture levels, using 15 participants. In the cases of frontal face and 5-degree face rotation views, the average recognition accuracies are 98.52% and 94.47% (no additional light sources), as well as 96.97% and 95.40% (two additional light sources), respectively. In addition, as an effective supplement to the problem of changes in illumination, the average recognition ratios are 96.23% and 96.20% under dry and wet face conditions, respectively. The experimental results reveal the robust performance of the proposed method in facial expression recognition.

Depth recovery for unstructured farmland road image using an improved SIFT algorithm

Road visual navigation relies on accurate road models. This study was aimed at proposing an improved scale-invariant feature transform (SIFT) algorithm for recovering depth information from farmland road images, which would provide a reliable path for visual navigation. The mean image of pixel value in five channels (R, G, B, S and V) were treated as the inspected image and the feature points of the inspected image were extracted by the Canny algorithm, for achieving precise location of the feature points and ensuring the uniformity and density of the feature points. The mean value of the pixels in 5×5 neighborhood around the feature point at an interval of 45o in eight directions was then treated as the feature vector, and the differences of the feature vectors were calculated for preliminary matching of the left and right image feature points. In order to achieve the depth information of farmland road images, the energy method of feature points was used for eliminating the mismatched points. Experiments with a binocular stereo vision system were conducted and the results showed that the matching accuracy and time consuming for depth recovery when using the improved SIFT algorithm were 96.48% and 5.6 s, respectively, with the accuracy for depth recovery of –7.17%-2.97% in a certain sight distance. The mean uniformity, time consuming and matching accuracy for all the 60 images under various climates and road conditions were 50%-70%, 5.0-6.5 s, and higher than 88%, respectively, indicating that performance for achieving the feature points (e.g., uniformity, matching accuracy, and algorithm real-time) of the improved SIFT algorithm were superior to that of conventional SIFT algorithm. This study provides an important reference for navigation technology of agricultural equipment based on machine vision. Keywords: scale-invariant feature transform (sift), feature matching, canny operator, energy method of feature point, farmland road, depth recovery, visual navigation DOI: 10.25165/j.ijabe.20191204.4821 Citation: Yao L J, Hu D, Yang Z D, Li H B, Qian M B. Depth recovery for unstructured farmland road image using an improved SIFT algorithm. Int J Agric & Biol Eng, 2019; 12(4): 141–147.

Memristor bridge-based low pass filter for image processing

This paper highlights the memristor bridge-based lowpass filter (LPF) and improved image processing algorithms along with a novel adaptive Gaussian filter for denoising image and a new Gaussian pyramid for scale invariant feature transform (SIFT). First, a novel kind of LPF based on the memristor bridge is designed, whose cut-off frequency and other traits are demonstrated to change with different time and memristance. In light of the changeable parameter of the memristor bridge-based LPF, a new adaptive Gaussian filter and an improved SIFT algorithm are presented. Finally, experiment results show that the peak signalto-noise ratio (PSNR) of our denoising is bettered more than 2.77 dB compared to the corresponding of the traditional Gaussian filter, and our improved SIFT performances including the number of matched feature points and the percent of correct matches are higher than the traditional SIFT, which verifies feasibility and effectiveness of our algorithm.

An improved SIFT algorithm based on adaptive fractional differential

Scale invariant feature transform (SIFT) has limitation in extracting features accurately for the images with small gradient and weak texture caused by low contrast. In order to tackle this problems, this paper proposes an improved SIFT algorithm based on adaptive fractional differential. The method firstly construct a mathematical model of adaptive fractional differential based on local image information, therefore, the relationship between the optimal order and image local information can be built up, and the optimal order at every pixel can be calculated automatically according to the characteristics of image. And an adaptive fractional differential dynamic mask is constructed in term of the optimal order and Riemann–Liouville (R–L) fractional definition. And then it is applied to SIFT algorithm for image matching. The method proposed in this paper is an important extension of SIFT algorithm. The theoretical analysis and experiment results indicate the proposed algorithm is capable of matching image with small gradient or weak texture or weak edge.

Research and Improvement of Content-Based Image Retrieval Framework

This paper proposed a high-performance image retrieval framework, which combines the improved feature extraction algorithm SIFT (Scale Invariant Feature Transform), improved feature matching, improved feature coding Fisher and improved Gaussian Mixture Model (GMM) for image retrieval. Aiming at the problem of slow convergence of traditional GMM algorithm, an improved GMM is proposed. This algorithm initializes the GMM by using on-line [Formula: see text]-means clustering method, which improves the convergence speed of the algorithm. At the same time, when the model is updated, the storage space is saved through the improvement of the criteria for matching rules and generating new Gaussian distributions. Aiming at the problem that the dimension of SIFT (Scale Invariant Feature Transform) algorithm is too high, the matching speed is too slow and the matching rate is low, an improved SIFT algorithm is proposed, which preserves the advantages of SIFT algorithm in fuzzy, compression, rotation and scaling invariance advantages, and improves the matching speed, the correct match rate is increased by an average of 40% to 55%. Experiments on a recently released VOC 2012 database and a database of 20 category objects containing 230,800 images showed that the framework had high precision and recall rates and less query time. Compared with the standard image retrieval framework, the improved image retrieval framework can detect the moving target quickly and effectively and has better robustness.

Binocular Stereo Vision Based Obstacle Detection Method for Manipulator

An obstacle detection method is proposed based on binocular stereo vision for manipulator. Firstly, images are preprocessed after camera calibration such as graying and distortion correction. Then, aiming at the defect that feature points are extracted mixed with many edge response points by traditional SIFT (Scale Invariant Feature Transform) algorithm, we propose wavelet transform to extract the edge points, and compare the edge points with feature points to further eliminate unstable feature points. Finally, the effectiveness of the algorithm is verified by obstacle detection and obstacle avoiding experiments. The results demonstrate that the improved SIFT algorithm can remove the edge responses that the DOG operator generates effectively, and improve the stability and anti-noise ability of SIFT algorithm compared with traditional SIFT algorithm.

An improved SIFT algorithm in the application of close-range Stereo image matching

As unmanned aerial vehicle (UAV) remote sensing is applied in small area aerial photogrammetry surveying, disaster monitoring and emergency command, 3D urban construction and other fields, the image processing of UAV has become a hot topic in current research. The precise matching of UAV image is a key problem, which affects the subsequent processing precision directly, such as 3D reconstruction and automatic aerial triangulation, etc. At present, SIFT (Scale Invariant Feature Transform) algorithm proposed by DAVID G. LOWE as the main method is, is widely used in image matching, since its strong stability to image rotation, shift, scaling, and the change of illumination conditions. It has been successfully applied in target recognition, SFM (Structure from Motion), and many other fields. SIFT algorithm needs the colour images to be converted into grayscale images, detects extremum points under different scales and uses neighbourhood pixels to generate descriptor. As we all know that UAV images with rich colour information, the SIFT algorithm improved through combining with the image colour information in this paper, the experiments are conducted from matching efficiency and accuracy compared with the original SIFT algorithm. The results show that the method which proposed in this paper decreases on the efficiency, but is improved on the precision and provides a basis choice for matching method.

Colour retinal fundus image registration by selecting stable extremum points in the scale‐invariant feature transform detector

A fundamental problem of image registration is the determination of corresponding points. The scale-invariant feature transform (SIFT) is a well-known algorithm in this regard. However, SIFT suffers from quantity, quality and distribution of the detected points when facing with high-resolution and low-contrast colour retinal fundus images. This study introduces an improved SIFT algorithm which identifies adequate, stable and distinctive keypoints with uniform distribution in the overlapped areas. The keypoint of the proposed method is a selection strategy of the difference of Gaussian (DoG) extremum points according to a stability score to guarantee the feature qualities. The stability score is based on the DoG values of extremum points and their vesselness measures in the relevant Gaussian images. Since the selected points lie on the vessels, which are relatively stable between image pairs, the points are unaffected by illumination and content variations of retinal backgrounds. The detected points are introduced to an integrated outlier rejection method. Then, the correspondences determine the geometric transformation parameters. The authors examined quantitatively and qualitatively the performance of this algorithm on four datasets including temporal and partially overlapping image pairs. The experimental results show the outperformance of the approach over similar methods in terms of efficiency, positional accuracy and speed.

Using an improved SIFT algorithm and fuzzy closed-loop control strategy for object recognition in cluttered scenes.

Partial occlusions, large pose variations, and extreme ambient illumination conditions generally cause the performance degradation of object recognition systems. Therefore, this paper presents a novel approach for fast and robust object recognition in cluttered scenes based on an improved scale invariant feature transform (SIFT) algorithm and a fuzzy closed-loop control method. First, a fast SIFT algorithm is proposed by classifying SIFT features into several clusters based on several attributes computed from the sub-orientation histogram (SOH), in the feature matching phase only features that share nearly the same corresponding attributes are compared. Second, a feature matching step is performed following a prioritized order based on the scale factor, which is calculated between the object image and the target object image, guaranteeing robust feature matching. Finally, a fuzzy closed-loop control strategy is applied to increase the accuracy of the object recognition and is essential for autonomous object manipulation process. Compared to the original SIFT algorithm for object recognition, the result of the proposed method shows that the number of SIFT features extracted from an object has a significant increase, and the computing speed of the object recognition processes increases by more than 40%. The experimental results confirmed that the proposed method performs effectively and accurately in cluttered scenes.

An improved image mosaic based on Canny edge and an 18-dimensional descriptor

To gain the wide view angle and high resolution image stitched by the sequence images overlapped in the same scene, this paper proposes a new image mosaic method of combining the improved SIFT algorithm with Canny feature edge detection based on the traditional scale invariant feature transform (SIFT) algorithm. First, we extract feature points of the image with the SIFT algorithm. Then, we construct an improved 18-dimensional feature descriptor consisting of 12 gradient values in a circular window, three cumulative gray-scale values and three gray-scale differences in a concentric circular window. Second, this method preserves the features in 16-neighborhood of the Canny edge image. Then, the extracted feature points search for the coarse matching points through the BBF, and the coarse matching points are purified with the random consistency (RANSAC) algorithm, which calculates the transformational matrix H among the images with these purified feature points. Finally, the seamless mosaic of images is completed with the image fusion algorithm of slipping in and out. In the experiment, we process the aerial image and the images that had changed in terms of translation, rotation and zoom, and parallax with the traditional SIFT and the proposed method, respectively. The results indicate that mosaic time, respectively reduced by 11.8%, 13.5%, 7.7% and 21.6%, the root mean squared error, respectively reduced by 80.1%, 0.002%, 4.4% and 58.1% through the proposed method in this paper, compared with the SIFT. Even for an image subjected to such situations as illumination, rotation, scaling and affine distortion, the matching performance can be improved with the proposed method.

An Improved SIFT Algorithm for Unmanned Aerial Vehicle Imagery

The Unmanned Aerial Vehicle (UAV) platform has the benefits of low cost and convenience compared with satellites. Recently, UAVs have shown a wide range of applications such as land use change, mineral resources management and local topographic mapping. Because of the instability of the UAV air gesture, an image matching method is necessary to match different images of an object or scene. Scale Invariant Feature Transform (SIFT) features are invariant to image scaling, rotation and translation. However, the main drawback of a SIFT algorithm is its significant memory consumption and low computational speed, particularly in the case of high-resolution imagery. In this study, in order to overcome these drawbacks, we have analysed the construction of the scale-space in the SIFT algorithm and selected new parameters to construct the SIFT scale-space to improve the memory consumption and computational speed for the processing of UAV imagery. Here, we propose a restriction on the number of octaves and levels for Gaussian image pyramids. Our experiment shows that the proposed algorithm effectively reduces memory consumption and significantly improves the operational efficiency of the feature point extraction and matching under the premise of maintaining the precision of the extracted feature points.

Using improved SIFT algorithm to implement surface defects detection for bridge cable

In order to realize automatic nondestructive testing for surface cable damage on a cablestayed bridge,a distributed machine vision system was developed.It uses four cameras to acquire images around the cable surface.Surface defection may be distributed in several images.An improved scale invariant feature transform(SIFT)feature matching algorithm for image mosaicing is proposed to real time processing to obtain a whole defect effectively.First,feature points are extracted by a Harris operator.Second,according to defect images collected by the system,the steps of the SIFT operator such as the distribution of the main direction for the matching feature points and the matching image rotation is simplified.The simplified SIFT operator is employed to describe the feature points and match the images.Finally,image fusion is implemented and a complete image of a defect is obtained.Experimental results show that the algorithm complexity is greatly reduced and improves detection integrity for surface cable defects using our improved SIFT to automaticslly stitch the defect images together.

应用尺度不变特征变换的多源遥感影像特征点匹配

Many traditional feature point algorithms can not handle more complex nonlinear brightness changes because the gray between multi-source remote sensing images is nonlinear changes.To cover the shortage,a Scale Invariant Feature Transform(SIFT)feature matching algorithm of multi-source remote sensing images was proposed.First,the approximate linear gray value between multi-source remote sensing images was achieved through linear fitting of the bands of the images.Then,an improved SIFT algorithm was adopted to match the fitted remote sensing images.Finally,the random sample Consensus algorithm was used to remove the false matching point pairs.In comparison with other feature matching algorithms(SIFT,Gradient Location Orientation Hologram(GLOH),RSSIFT).The experimental results show that the feature matching rate increases by about 4% between ETM+ panchromatic and multispectral images and the number of correct matches of key points increases by about 8point pairs between CBERS-02Band HJ-1Bimages.It concludes that the proposed method significantly outperforms many state-of-the-art methods under multi-source remote sensing images.

Uniform Robust Scale-Invariant Feature Matching for Optical Remote Sensing Images

Extracting well-distributed, reliable, and precisely aligned point pairs for accurate image registration is a difficult task, particularly for multisource remote sensing images that have significant illumination, rotation, and scene differences. The scale-invariant feature transform (SIFT) approach, as a well-known feature-based image matching algorithm, has been successfully applied in a number of automatic registration of remote sensing images. Regardless of its distinctiveness and robustness, the SIFT algorithm suffers from some problems in the quality, quantity, and distribution of extracted features particularly in multisource remote sensing imageries. In this paper, an improved SIFT algorithm is introduced that is fully automated and applicable to various kinds of optical remote sensing images, even with those that are five times the difference in scale. The main key of the proposed approach is a selection strategy of SIFT features in the full distribution of location and scale where the feature qualities are quarantined based on the stability and distinctiveness constraints. Then, the extracted features are introduced to an initial cross-matching process followed by a consistency check in the projective transformation model. Comprehensive evaluation of efficiency, distribution quality, and positional accuracy of the extracted point pairs proves the capabilities of the proposed matching algorithm on a variety of optical remote sensing images.