Interest Point Feature Research Articles

Interest Point Selection and Feature Extraction in Six-DoF Grasp Pose Detection

Interest Point Selection and Feature Extraction in Six-DoF Grasp Pose Detection

A Tourist Attractions Recommendation Model Based on Sequence Interest Extraction and Location Information Fusion

Travel, as one way to relax oneself, has become the first choice for people to enjoy their body and mind in modern society. However, while facing lots of information, how to help users make better decisions on their next travel goals through their historical interest spots is a direction that needs further research in big data recommendation systems. In this thesis, we proposed the deep convolution and multi-head self-attention position network model. First, it extracts the user’s historical interest point feature information by convolutional neural network method, and then performs horizontal and vertical filtering. Next, it interacts the obtained information with the candidate attraction information, and extracts the location information of the historical interest sequence by the multi-head self-attention mechanism. Finally, the model does the attention mechanism of the candidate attraction by fusing the feature information of the location information. The final model achieves a deep fusion of user sequence interest and location feature information. We conducted detailed comparison experiments with the very popular models in the industry on different public datasets, and the results showed that our deep convolution and multi-head self-attention position network model has good performance.

An RFID-Enabled IoT-Based Smart Tourist Route Recommendation Algorithm

With the rapid development and broad deployment of Internet of Things (IoT) technologies, the IoT are increasingly shifting away from “interconnection of everything” to “human-computer-thing” sensing integration. Although there are numerous sensing technologies available today, radio frequency identification (RFID) has emerged as useful medium for “passive sensing” due to its lightweight, taggable, and simple deployment properties. With the growth of social networks in recent years, it has become a significant research hotspot for the development of path suggestion systems that are tailored to the demands of individual users’ preferences. This paper considers the relevant features of interest points, integrates the user’s emotion and product similarity into the heuristic function of the ant colony algorithm, adopts the elite management ant strategy, maximizes the management ant strategy, and uses particle swarm algorithm to improve the initial pheromone distribution of the ant colony algorithm. The proposed model combines the ratings of 593 tourists and text comment information into one dataset and proposes a smart tourist route recommendation model. The improved ant colony algorithm is utilized to recommend the most popular tourist routes and recommend the tourist routes of the most popular tourist spots in the scenic area. The suggested method is more efficient in terms of accuracy and recall. The F measure value is derived from real-world dataset testing.

Implementasi Algoritma Speeded Up Robust Features (SURF) Pada Pengenalan Rambu – Rambu Lalu Lintas

One factor of increased violations on the highway is a violation of traffic signs, because the signs are not visible to the driver. In addition to this the conditions on road signs attached to the road have shortcomings such as twisting signs, imperfect beacons and non-standard beacons. So to be able to reduce the violation of traffic signs required a system that can recognize traffic. To be able to recognize traffic signs can be done visually and must be fast in recognizing. The image to be recognized can use the camera to retrieve information from signposts then the image is extracted with features of Speeded Up Robust Features (SURF) algorithm consisting of three stages: interest point detection, scale space, feature description and feature matching so that the system can recognize traffic signs. The research that has been done has resulted that the SURF algorithm in recognizing traffic signs is good enough to be the algorithm of introduction of traffic signs with the need to be fast and accurate. In addition, this algorithm is invariant to scale and invariant to rotation, so that the difference of slope and scale difference can still be recognized by using SURF algorithm

Detection of axonal synapses in 3D two-photon images.

Studies of structural plasticity in the brain often require the detection and analysis of axonal synapses (boutons). To date, bouton detection has been largely manual or semi-automated, relying on a step that traces the axons before detection the boutons. If tracing the axon fails, the accuracy of bouton detection is compromised. In this paper, we propose a new algorithm that does not require tracing the axon to detect axonal boutons in 3D two-photon images taken from the mouse cortex. To find the most appropriate techniques for this task, we compared several well-known algorithms for interest point detection and feature descriptor generation. The final algorithm proposed has the following main steps: (1) a Laplacian of Gaussian (LoG) based feature enhancement module to accentuate the appearance of boutons; (2) a Speeded Up Robust Features (SURF) interest point detector to find candidate locations for feature extraction; (3) non-maximum suppression to eliminate candidates that were detected more than once in the same local region; (4) generation of feature descriptors based on Gabor filters; (5) a Support Vector Machine (SVM) classifier, trained on features from labelled data, and was used to distinguish between bouton and non-bouton candidates. We found that our method achieved a Recall of 95%, Precision of 76%, and F1 score of 84% within a new dataset that we make available for accessing bouton detection. On average, Recall and F1 score were significantly better than the current state-of-the-art method, while Precision was not significantly different. In conclusion, in this article we demonstrate that our approach, which is independent of axon tracing, can detect boutons to a high level of accuracy, and improves on the detection performance of existing approaches. The data and code (with an easy to use GUI) used in this article are available from open source repositories.

Affine Invariant Description and Large-Margin Dimensionality Reduction for Target Detection in Optical Remote Sensing Images

A novel target detection method based on affine invariant interest point detection, feature encoding, and large-margin dimensionality reduction (LDR) is proposed for optical remote sensing images. First, four types of interest point detectors are introduced, and their performance in extracting low-level affine invariant descriptors using affine shape estimation is compared. Such a description can deal with significant affine transformations, including viewpoints. Second, feature encoding, which extends bag-of-words (BOW) by encoding high-order statistics, is selected to generate mid-level representation. Finally, LDR based on the large-margin constraint and stochastic subgradient is introduced to make the high-dimensional mid-level representation applicable for target detection. The experiments on aircraft and vehicle detections illustrate the effectiveness of the affine invariant description and LDR (compared with principal component analysis) in improving the detection performance. The experiments also demonstrate the effectiveness of the proposed method compared with popular approaches including Gabor, HOG, LBP, BOW, and R-CNN.

Video-based slip sensor for multidimensional information detecting in deformable object grasp

Efficient and reliable slip sensor plays a critical role in grasp of deformable object. This paper provides a new method for slip detection based on video processing, which can offer multidimensional sensing information and it is applicable for gripping deformable objects. The macro camera mounted inside the gripper can capture the dynamic slip and distortion of the object. The features of interest points, detected by the SURF algorithm in subsequent frames, are used to identify the properties of object and calculate the object’s changes. To determine the object’s slippage, nine detecting windows in the camera view can detect nine tracks of the slippage. Besides, the object’s distortion and direction of tangential force on the surface can be determined from these tracks, which helps to the estimation of the object’s damage. Experiments on homogeneous and textured materials show that this method can detect the object’ slippage accurately, and meanwhile provides the tracks of the slippage, distortion information and the force situation. Furthermore, tests for comparison were carried out and the results show that this sensor has a high accuracy in detecting slippage and distortion and the error is acceptable, which has an significant impact in deformable object grasp.

Two‐layer discriminative model for human activity recognition

Most of recent methods for action/activity recognition, usually based on static classifiers, have achieved improvements by integrating context of local interest point (IP) features such as spatiotemporal IPs by characterising their neighbourhood under different scales. In this study, the authors propose a new approach that explicitly models the sequential aspect of activities. First, a sliding window segmentation technique splits the video stream into overlapping short segments. Each window is characterised by a local bag of words of IPs encoded by motion information. A first-layer support vector machine provides for each window a vector of conditional class probabilities that summarises all discriminant information that is relevant for sequence recognition. The sequence of these stochastic vectors is then fed to a hidden conditional random field for inference at the sequence level. They also show how their approach can be naturally extended to the problem of conjoint segmentation and recognition of a sequence of action classes within a continuous video stream. They have tested their model on various human action and activity datasets and the obtained results compare favourably with current state of the art.

Guest Editorial Special Issue on Mobile Biometrics

Guest Editorial Special Issue on Mobile Biometrics

Descriptor evaluation and feature regression for multimodal image analysis

In this paper, we present feature descriptor evaluation and feature regression for multimodal image analysis. First, we compare the performances of several popular interest point detectors and feature descriptors from multimodal images with focus on visual and infrared images. The performances of detectors are evaluated mainly by the score of repeatability and accuracy and the descriptors are assessed by using the rate of precision and recall. Secondly, we analyze the relationship between the corresponding descriptors computed from multimodal images. The descriptors are regressed by means of linear regression as well as Gaussian process. Then the features on infrared images are predicted by mapping the descriptors from visual images to the infrared modality through the regression results. Predictions are assessed in two ways: the statistics of absolute error between true values and actual values, and the precision score of matching the predicted descriptors to the original infrared descriptors. We believe that this evaluating information will be useful when selecting an appropriate detector and descriptor for multimodal image analysis. Also the experimental results show that regression methods achieve a well-assessed relationship between corresponding descriptors from multiple modalities.

Recognizing human interactions by genetic algorithm-based random forest spatio-temporal correlation

Recognizing human interactions is a more challenging task than recognizing single person activities and has attracted much attention of the computer vision community. This paper proposes an innovative and effective way to recognize human interactions, which incorporates the advantages of both global motion context (MC) feature and spatio-temporal (S-T) correlation of local spatio-temporal interest point feature. The MC feature is used to train a random forest where genetic algorithm (GA) is applied to the training phase to achieve a good compromise between reliability and efficiency. Besides, we propose S-T correlation-based match, where MC's structure and Needleman---Wunsch algorithm are used to calculate the spatial and temporal correlation score of two videos, respectively. Experiments on the UT-Interaction dataset show that our approaches outperform other prevalent machine learning methods, and that the combination of GA search-based random forest and S-T correlation achieves the state-of-the-art performance.

Texture-based fruit detection

In this paper, a technique based on texture analysis is proposed for detecting green fruits on plants. The method involves interest point feature extraction and descriptor computation, interest point classification using support vector machines, candidate fruit point mapping, morphological closing and fruit region extraction. In an empirical study using low-cost web camera sensors suitable for use in mechanized systems, 24 combinations of interest point features and interest point descriptors were evaluated on two fruit types (pineapple and bitter melon). The method is highly accurate, with single-image detection rates of 85 % for pineapples and 100 % for bitter melons. The method is thus sufficiently accurate for precise location and monitoring of textured fruit in the field. Future work will explore combination of detection and tracking for further improved results.

Projection transform on spatio-temporal context for action recognition

This paper discusses the task of human action recognition. This task is important to applications like video surveillance and video retrieval. Most of the existing local interest points based works on human action analysis, lost the information about spatio-temporal distribution of features and neglected the relationship between features and each defined actions. In this paper, through the analysis of feature distribution and their interactions over spatio-temporal domain, we propose a novel projection transform to take the two factors into account. A video sequence of human action in our perspective can be modeled by three types of features of spatio-temporal interest points: the global projection transform feature, the relative position distribution feature and the bag of visual words based feature. Then a new context-K-nearest-neighbor classifier is utilized to fuse them to form discriminative feature sets for action matching. In most of the case, our experiments have indicated that the novel method outperforms other previous published results on the Weizmann and KTH datasets.

Visual Typo Correction by Collocative Optimization: A Case Study on Merchandize Images.

Near-duplicate retrieval (NDR) in merchandize images is of great importance to a lot of online applications on e-Commerce websites. In those applications where the requirement of response time is critical, however, the conventional techniques developed for a general purpose NDR are limited, because expensive post-processing like spatial verification or hashing is usually employed to compromise the quantization errors among the visual words used for the images. In this paper, we argue that most of the errors are introduced because of the quantization process where the visual words are considered individually, which has ignored the contextual relations among words. We propose a "spelling or phrase correction" like process for NDR, which extends the concept of collocations to visual domain for modeling the contextual relations. Binary quadratic programming is used to enforce the contextual consistency of words selected for an image, so that the errors (typos) are eliminated and the quality of the quantization process is improved. The experimental results show that the proposed method can improve the efficiency of NDR by reducing vocabulary size by 1000% times, and under the scenario of merchandize image NDR, the expensive local interest point feature used in conventional approaches can be replaced by color-moment feature, which reduces the time cost by 9202% while maintaining comparable performance to the state-of-the-art methods.

Image retrieval based on combined features of interest points

Due to the spatial distribution expression power of the ring areas,this paper proposed a new image retrieval algorithm based on color feature and texture feature of interest points,introducing the ring area into the Gabor wavelet texture features.At first,this algorithm used adaptive smoothing filter to eliminate noises and detected interest points by the Speeded Up Robust Feature(SURF) operator.Then,it calculated the color histogram and texture feature of interest points in the ring area,as image's combined features.Finally,it output similar images according to the similarity of the combined features.The experimental results show that this algorithm improves the average retrieval accuracy by more than 7%.

Robust color image retrieval using visual interest point feature of significant bit-planes

In this paper, we propose a robust color image retrieval method using visual interest point feature of significant bit-planes. We firstly extract the visually significant bit-plane image from the original color image according to the bit-plane theory and noise attack characteristic. And then, we extract the visual interest points from the original color image by using the significant bit-plane image and multi-scale Harris–Laplace detector, and construct the fuzzy color histogram of visual interest points. We finally compute the similarity between color images by using the fuzzy color histogram of visual interest points. Experiments on large databases show that the proposed algorithm is significantly more effective than the state-of-the-art approaches. Especially, it can retrieve the noise-attacked (including blurring, sharpening, and illumination, etc.) image effectively. ► To extract the visual interest points from the original color image by using the significant bit-plane image and multi-scale Harris–Laplace detector. ► To construct the fuzzy color histogram of visual interest points. ► To compute the similarity between color images by using the fuzzy color histogram of visual interest points.

LF-EME: Local features with elastic manifold embedding for human action recognition

Human action recognition has been an active topic in computer vision. Currently, most of the approaches to this problem can be categorized into two classes. One is based on local features, and the other is based on global features. Meanwhile, manifold learning has become successful in many problems in computer vision, but because of the high variability of human body, the application of manifold learning to human action recognition is limited. We propose a framework based on Elastic Manifold Embedding (EME), a new sparse manifold learning algorithm, together with local interest point features to handle human action recognition. The result of the new framework is very promising in comparison with state-of-the-art methods.

An Image Retrieval Method Based on Local Features of Interest Points

To measure the similarity between two images, the local information around all the points were usually used for traditional image retrieval methods based on interest points. The accuracy would be influenced by the dissimilar interest points in the background region or in the uninterested regions. A new image retrieval method based on interest points was proposed in this paper. The most similar interest points were chosen firstly based on feature matching techniques, then the similarity was measured based on the local gray information around the preserved similar interest points. Experiments show that the proposed method is more accurate than traditional image retrieval method based on interest points.

Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking

Applications for real-time visual tracking can be found in many areas, including visual odometry and augmented reality. Interest point detection and feature description form the basis of feature-based tracking, and a variety of algorithms for these tasks have been proposed. In this work, we present (1) a carefully designed dataset of video sequences of planar textures with ground truth, which includes various geometric changes, lighting conditions, and levels of motion blur, and which may serve as a testbed for a variety of tracking-related problems, and (2) a comprehensive quantitative evaluation of detector-descriptor-based visual camera tracking based on this testbed. We evaluate the impact of individual algorithm parameters, compare algorithms for both detection and description in isolation, as well as all detector-descriptor combinations as a tracking solution. In contrast to existing evaluations, which aim at different tasks such as object recognition and have limited validity for visual tracking, our evaluation is geared towards this application in all relevant factors (performance measures, testbed, candidate algorithms). To our knowledge, this is the first work that comprehensively compares these algorithms in this context, and in particular, on video streams.

A feature-based matching scheme: MPCD and robust matching strategy

This paper presents a scheme that matches interest point features detected on two images taken from different points of view. To accomplish this objective, we jointly consider the corner detection and matching problems. Firstly, a new multi-scale Plessey corner detector (MPCD) is used to detect the interest points. Secondly, the geometric constraint between two images is exploited, based on which we propose a new energy function that can approximate 2D affine transformation in a more efficient way. Only a small set of corners with the highest accuracy and robustness are considered in the first stage, consequently, a small data space is provided to the robust algorithm in the second stage reducing the computation time. Therefore, more information can be incorporated into our scheme based on corner detection and matching phases. We compare our method using the proposed MPCD with two standard corner detectors based on image matching. We also evaluate our proposed matching strategy against Zhengyou’s method [Deriche, R., Zhang, Z., Luong, Q.-T., Faugeras, O., 1994. Robust recovery of the epipolar geometry for an uncalibrated stereo rig. In: European Conference on Computer Vision, Stockholm, Sweden, pp. 567–576]. Our scheme provides a new viewpoint and better results for the traditional feature matching problem.