3D clothing fitting based on the geometric feature matching

Accurate and reliable state estimation and mapping are the foundation of most autonomous driving systems. In recent years, researchers have focused on pose estimation through geometric feature matching. However, most of the works in the literature assume a static scenario. Moreover, a registration based on a geometric feature is vulnerable to the interference of a dynamic object, resulting in a decline of accuracy. With the development of a deep semantic segmentation network, we can conveniently obtain the semantic information from the point cloud in addition to geometric information. Semantic features can be used as an accessory to geometric features that can improve the performance of odometry and loop closure detection. In a more realistic environment, semantic information can filter out dynamic objects in the data, such as pedestrians and vehicles, which lead to information redundancy in generated map and map-based localization failure. In this paper, we propose a method called LiDAR inertial odometry (LIO) with loop closure combined with semantic information (LIO-CSI), which integrates semantic information to facilitate the front-end process as well as loop closure detection. First, we made a local optimization on the semantic labels provided by the Sparse Point-Voxel Neural Architecture Search (SPVNAS) network. The optimized semantic information is combined into the front-end process of tightly-coupled light detection and ranging (LiDAR) inertial odometry via smoothing and mapping (LIO-SAM), which allows us to filter dynamic objects and improve the accuracy of the point cloud registration. Then, we proposed a semantic assisted scan-context method to improve the accuracy and robustness of loop closure detection. The experiments were conducted on an extensively used dataset KITTI and a self-collected dataset on the Jilin University (JLU) campus. The experimental results demonstrate that our method is better than the purely geometric method, especially in dynamic scenarios, and it has a good generalization ability.

Download Full-text

Recognition and Grasping of Disorderly Stacked Wood Planks Using a Local Image Patch and Point Pair Feature Method

Sensors ◽

10.3390/s20216235 ◽

2020 ◽

Vol 20 (21) ◽

pp. 6235

Author(s):

Chengyi Xu ◽

Ying Liu ◽

Fenglong Ding ◽

Zilong Zhuang

Keyword(s):

Feature Matching ◽

Recognition Rate ◽

Image Features ◽

Geometric Feature ◽

Feature Descriptor ◽

Image Patch ◽

Feature Description ◽

Point Pair ◽

Image Patches ◽

Local Image

Considering the difficult problem of robot recognition and grasping in the scenario of disorderly stacked wooden planks, a recognition and positioning method based on local image features and point pair geometric features is proposed here and we define a local patch point pair feature. First, we used self-developed scanning equipment to collect images of wood boards and a robot to drive a RGB-D camera to collect images of disorderly stacked wooden planks. The image patches cut from these images were input to a convolutional autoencoder to train and obtain a local texture feature descriptor that is robust to changes in perspective. Then, the small image patches around the point pairs of the plank model are extracted, and input into the trained encoder to obtain the feature vector of the image patch, combining the point pair geometric feature information to form a feature description code expressing the characteristics of the plank. After that, the robot drives the RGB-D camera to collect the local image patches of the point pairs in the area to be grasped in the scene of the stacked wooden planks, also obtaining the feature description code of the wooden planks to be grasped. Finally, through the process of point pair feature matching, pose voting and clustering, the pose of the plank to be grasped is determined. The robot grasping experiment here shows that both the recognition rate and grasping success rate of planks are high, reaching 95.3% and 93.8%, respectively. Compared with the traditional point pair feature method (PPF) and other methods, the method present here has obvious advantages and can be applied to stacked wood plank grasping environments.

Download Full-text

Research on the Recognition Technology of Letter String on Label

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.476-478.876 ◽

2012 ◽

Vol 476-478 ◽

pp. 876-880

Author(s):

Yu Chan Xie ◽

Wei Jin

Keyword(s):

Projection Method ◽

Feature Matching ◽

Small Region ◽

Letter Recognition ◽

Geometric Feature ◽

Theory Analysis ◽

Recognition Method ◽

Matching Process ◽

Straight Line ◽

Single Character

A letters recognition method based on a small area of the feature matching is proposed, in which the unqualified letter in the string were recognized based on its geometric feature. In this method, firstly confirm label’s position by the extracted straight line characters. Then, rotate and zoom image according to the prior knowledge of label. Acquire the position of the string on the label and cut them out. And then single letters are segmented out using the projection method in the area of the string. Finally, compare geometrical characteristics of the extracted letters with its template to recognize and eliminate unqualified labels. The matching process proceeded only in the small region with letters and there is no need to search the irrelevant information. For this algorithm, so much time has been saved compared with traditional letter recognition method and projection method which is used for single character segmentation is very quick also. Theory analysis and experiment showed that the method can segment unqualified characters robustly and quickly.

Download Full-text

Fast Aerial Image Geolocalization Using the Projective-Invariant Contour Feature

Remote Sensing ◽

10.3390/rs13030490 ◽

2021 ◽

Vol 13 (3) ◽

pp. 490

Author(s):

Yongfei Li ◽

Shicheng Wang ◽

Hao He ◽

Deyu Meng ◽

Dongfang Yang

Keyword(s):

Feature Matching ◽

Projective Transformation ◽

Aerial Image ◽

Geometric Feature ◽

Point Set Registration ◽

Projective Invariant ◽

Geometric Consistency ◽

Local Point ◽

Contour Feature ◽

Point Set

We address the problem of aerial image geolocalization over an area as large as a whole city through road network matching, which is modeled as a 2D point set registration problem under the 2D projective transformation and solved in a two-stage manner. In the first stage, all the potential transformations aligning the query road point set to the reference road point set are found by local point feature matching. A local geometric feature, called the Projective-Invariant Contour Feature (PICF), which consists of a road intersection and the closest points to it in each direction, is specifically designed. We prove that the proposed PICF is equivariant under the 2D projective transformation group. We then encode the PICF with a projective-invariant descriptor to enable the fast search of potential correspondences. The bad correspondences are then removed by a geometric consistency check with the graph-cut algorithm effectively. In the second stage, a flexible strategy is developed to recover the homography transformation with all the PICF correspondences with the Random Sample Consensus (RANSAC) method or to recover the transformation with only one correspondence and then refine it with the local-to-global Iterative Closest Point (ICP) algorithm when only a few correspondences exist. The strategy makes our method efficient to deal with both scenes where roads are sparse and scenes where roads are dense. The refined transformations are then verified with alignment accuracy to determine whether they are accepted as correct. Experimental results show that our method runs faster and greatly improves the recall compared with the state-of-the-art methods.

Download Full-text

Word-Finding Support From Mobile Technology Benefits a Woman With Aphasia

Perspectives on Augmentative and Alternative Communication ◽

10.1044/aac24.1.26 ◽

2015 ◽

Vol 24 (1) ◽

pp. 26-39 ◽

Cited By ~ 1

Author(s):

Yvonne Gillette

Keyword(s):

Mobile Technology ◽

Clinical Education ◽

Augmentative And Alternative Communication ◽

Feature Matching ◽

Mobile Technologies ◽

Alternative Communication ◽

Alternative Intervention ◽

Communication Assessment ◽

Word Finding ◽

Intervention Costs

Mobile technology provides a solution for individuals who require augmentative and alternative intervention. Principles of augmentative and alternative communication assessment and intervention, such as feature matching and the participation model, developed with dedicated speech-generating devices can be applied to these generic mobile technologies with success. This article presents a clinical review of an adult with aphasia who reached her goals for greater communicative participation through mobile technology. Details presented include device selection, sequence of intervention, and funding issues related to device purchase and intervention costs. Issues related to graduate student clinical education are addressed. The purpose of the article is to encourage clinicians to consider mobile technology when intervening with an individual diagnosed with mild receptive and moderate expressive aphasia featuring word-finding difficulties.

Download Full-text

Recognition of Birds in Blurred and Illumination Images by Local Features

International Journal of Advanced Research in Computer Science and Software Engineering ◽

10.23956/ijarcsse/v7i7/0128 ◽

2017 ◽

Vol 7 (7) ◽

pp. 243

Author(s):

Suresha .M ◽

. Sandeep

Keyword(s):

Computer Vision ◽

Time Complexity ◽

Feature Detection ◽

Feature Matching ◽

Fast Algorithms ◽

Local Features ◽

Experimental Demonstration ◽

Harris Corner ◽

Blurred Image ◽

Blurred Images

Local features are of great importance in computer vision. It performs feature detection and feature matching are two important tasks. In this paper concentrates on the problem of recognition of birds using local features. Investigation summarizes the local features SURF, FAST and HARRIS against blurred and illumination images. FAST and Harris corner algorithm have given less accuracy for blurred images. The SURF algorithm gives best result for blurred image because its identify strongest local features and time complexity is less and experimental demonstration shows that SURF algorithm is robust for blurred images and the FAST algorithms is suitable for images with illumination.

Download Full-text

Separating Multiple Moving Sources by Microphone Array Signals for Wayside Acoustic Fault Diagnosis

Journal of Vibration and Acoustics ◽

10.1115/1.4043508 ◽

2019 ◽

Vol 141 (5) ◽

Author(s):

Wei Xiong ◽

Qingbo He ◽

Zhike Peng

Keyword(s):

Fault Diagnosis ◽

Time Domain ◽

Feature Matching ◽

Matching Pursuit ◽

Microphone Array ◽

Time Frequency ◽

Moving Sources ◽

The Time Domain ◽

Envelope Spectrum ◽

Threshold Setting

Wayside acoustic defective bearing detector (ADBD) system is a potential technique in ensuring the safety of traveling vehicles. However, Doppler distortion and multiple moving sources aliasing in the acquired acoustic signals decrease the accuracy of defective bearing fault diagnosis. Currently, the method of constructing time-frequency (TF) masks for source separation was limited by an empirical threshold setting. To overcome this limitation, this study proposed a dynamic Doppler multisource separation model and constructed a time domain-separating matrix (TDSM) to realize multiple moving sources separation in the time domain. The TDSM was designed with two steps of (1) constructing separating curves and time domain remapping matrix (TDRM) and (2) remapping each element of separating curves to its corresponding time according to the TDRM. Both TDSM and TDRM were driven by geometrical and motion parameters, which would be estimated by Doppler feature matching pursuit (DFMP) algorithm. After gaining the source components from the observed signals, correlation operation was carried out to estimate source signals. Moreover, fault diagnosis could be carried out by envelope spectrum analysis. Compared with the method of constructing TF masks, the proposed strategy could avoid setting thresholds empirically. Finally, the effectiveness of the proposed technique was validated by simulation and experimental cases. Results indicated the potential of this method for improving the performance of the ADBD system.

Download Full-text