scholarly journals Visual-Based Localization Using Pictorial Planar Objects in Indoor Environment

2020 ◽  
Vol 10 (23) ◽  
pp. 8583
Author(s):  
Yu Meng ◽  
Kwei-Jay Lin ◽  
Bo-Lung Tsai ◽  
Ching-Chi Chuang ◽  
Yuheng Cao ◽  
...  
Keyword(s):  
Object Localization ◽  
Detection Methods ◽  
Feature Points ◽  
Planar Surface ◽  
Binary Marker ◽  
Smart Services ◽  
3D Space ◽  
Camera View ◽  
Original Picture ◽  
Localization Approach

Localization is an important technology for smart services like autonomous surveillance, disinfection or delivery robots in future distributed indoor IoT applications. Visual-based localization (VBL) is a promising self-localization approach that identifies a robot’s location in an indoor or underground 3D space by using its camera to scan and match the robot’s surrounding objects and scenes. In this study, we present a pictorial planar surface based 3D object localization framework. We have designed two object detection methods for localization, ArPico and PicPose. ArPico detects and recognizes framed pictures by converting them into binary marker codes for matching with known codes in the library. It then uses the corner points on a picture’s border to identify the camera’s pose in the 3D space. PicPose detects the pictorial planar surface of an object in a camera view and produces the pose output by matching the feature points in the view with that in the original picture and producing the homography to map the object’s actual location in the 3D real world map. We have built an autonomous moving robot that can self-localize itself using its on-board camera and the PicPose technology. The experiment study shows that our localization methods are practical, have very good accuracy, and can be used for real time robot navigation.

scholarly journals LEARNING MAPS FOR OBJECT LOCALIZATION USING VISUAL-INERTIAL ODOMETRY

2020 ◽  
Vol V-1-2020 ◽  
pp. 343-350
Author(s):  
B. Zha ◽  
A. Yilmaz
Keyword(s):  
Object Motion ◽  
Spatial Uncertainty ◽  
Object Localization ◽  
Abstract Objects ◽  
Motion Patterns ◽  
Localization Accuracy ◽  
Single Location ◽  
Trajectory Classification ◽  
Potential Motion ◽  
Localization Approach

Abstract. Objects follow designated path on maps, such as vehicles travelling on a road. This observation signifies topological representation of objects’ motion on the map. Considering the position of object is unknown initially, as it traverses the map by moving and turning, the spatial uncertainty of its whereabouts reduces to a single location as the motion trajectory would fit only to a certain map trajectory. Inspired by this observation, we propose a novel end-to-end localization approach based on topological maps that exploits the object motion and learning the map using an recurrent neural network (RNN) model. The core of the proposed method is to learn potential motion patterns from the map and perform trajectory classification in the map’s edge-space. Two different trajectory representations, namely angle representation and augmented angle representation (incorporates distance traversed) are considered and an RNN is trained from the map for each representation to compare their performances. The localization accuracy in the tested map for the angle and augmented angle representations are 90.43% and 96.22% respectively. The results from the actual visual-inertial odometry have shown that the proposed approach is able to learn the map and localize objects based on their motion.

scholarly journals A Mountain Summit Recognition Method Based on Improved Faster R-CNN

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Yueping Kong ◽  
Yun Wang ◽  
Song Guo ◽  
Jiajing Wang
Keyword(s):  
Detection Methods ◽  
Feature Points ◽  
Feature Maps ◽  
Recognition Method ◽  
Objective Criterion ◽  
Detection Algorithms ◽  
Digital Elevation ◽  
Feature Pyramid ◽  
Mountain Summit ◽  
Elevation Model

Mountain summits are vital topographic feature points, which are essential for understanding landform processes and their impacts on the environment and ecosystem. Traditional summit detection methods operate on handcrafted features extracted from digital elevation model (DEM) data and apply parametric detection algorithms to locate mountain summits. However, these methods may no longer be effective to achieve desirable recognition results in small summits and suffer from the objective criterion lacking problem. Thus, to address these problems, we propose an improved Faster region-convolutional neural network (R-CNN) to accurately detect the mountain summits from DEM data. Based on Faster R-CNN, the improved network adopts a residual convolution block to replace the traditional part and adds a feature pyramid network (FPN) to fuse the features with adjacent layers to better address the mountain summit detection task. The residual convolution is employed to capture the deep correlation between visual and physical morphological features. The FPN is utilized to integrate the location and semantic information in the extracted feature maps to effectively represent the mountain summit area. The experimental results demonstrate that the proposed network could achieve the highest recall and precision without manually designed summit features and accurately identify small summits.

A Skew Detection Algorithm for PDF417 Based on Feature Point

2011 ◽  
Vol 128-129 ◽  
pp. 495-499
Author(s):  
Jian Hua Li ◽  
Ping Li ◽  
Xiao Dan Li ◽  
Yi Wen Wang
Keyword(s):  
Least Square Method ◽  
Detection Algorithm ◽  
Least Square ◽  
Detection Methods ◽  
Automatic Identification ◽  
Feature Points ◽  
Skew Angle ◽  
Bar Code ◽  
Character Code ◽  
The Common

The automatic identification of 2D (two dimensional) bar code PDF417 is very sensitive to skew angle, but, the common skew angle detection methods have shortcomings such as weak performance in time complexity. In this paper, based on the properties of PDF417 character code and the extraction of feature points, we get skew angle of PDF417 bar code image using the least square method. Experiments show that this algorithm has virtue of less computation and high accuracy.

scholarly journals COMPARISON OF PIXEL-BASED AND FEATURE-BASED APPROACH FOR SMALL OBJECT CHANGE DETECTION

2021 ◽  
Vol XLIII-B3-2021 ◽  
pp. 353-357
Author(s):  
J. Seo ◽  
T. Kim
Keyword(s):  
Change Detection ◽  
Satellite Images ◽  
Rate Of Change ◽  
Image Resolution ◽  
Detection Methods ◽  
Small Object ◽  
Feature Points ◽  
Detection Algorithms ◽  
Change Detection Algorithms ◽  
Feature Based

Abstract. Satellite image resolution has evolved to daily revisit and sub-meter GSD. Main targets of previous remote sensing were forest, vegetation, damage area by disasters, land use and land cover. Developments in satellite images have brought expectations on more sophisticated and various change detection of objects. Accordingly, we focused on unsupervised change detection of small objects, such as vehicles and ships. In this paper, existing change detection methods were applied to analyze their performances for pixel-based and feature-based change of small objects. We used KOMPSAT-3A images for tests. Firstly, we applied two change detection algorithms, MAD and IR-MAD, which are most well-known pixel-based change detection algorithms, to the images. We created a change magnitude map using the change detection methods. Thresholding was applied to determine change and non-change pixels. Next, the satellite images were transformed as 8-bit images for extracting feature points. We extracted feature points using SIFT and SURF methods to analyze feature-based change detection. We assumed to remove false alarms by eliminating feature points of non-changed objects. Therefore, we applied a feature-based matcher and matched feature points on identical image locations were eliminated. We used non-matched feature points for change/non-change analysis. We observed changes by creating a 5x5 size ROI around extracted feature points in the change/non-change map. We determined that change has occurred on feature points if the rate of change pixels with ROI was more than 50%. We analyzed the performance of pixel-based and feature-based change detection using ground truths. The F1-score, AUC value, and ROC were used to compare the performance of change detection. Performance showed that feature-based approaches performed better than pixel-based approaches.

Extraction of Mountain Feature Line Based on 3D Laser Scanning

2012 ◽  
Vol 182-183 ◽  
pp. 1821-1825 ◽  
Author(s):  
Cheng Hui Wan ◽  
Xiao Jun Cheng
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Point Cloud Data ◽  
Feature Points ◽  
3D Laser Scanning ◽  
Cloud Data ◽  
3D Space ◽  
Contour Lines ◽  
Feature Line ◽  
Cut Surface

This paper applies a Cut-and-Sew algorithm extracting feature line of the mountain based on laser 3D scanning. The mountain is cut at the direction of contour lines. Point cloud data of the cut surface fits curve that project the same plane. Feature points find the curve corresponding to match. Through the connection of feature points, then returning the 3D space to achieve feature line, and the establishment of the formation of the triangular feature line is reconstructed on the mountain.

scholarly journals Moving Object Detection for Video Surveillance

2015 ◽  
Vol 2015 ◽  
pp. 1-10 ◽  
Author(s):  
K. Kalirajan ◽  
M. Sudha
Keyword(s):  
Object Detection ◽  
Video Compression ◽  
Video Surveillance ◽  
Statistical Correlation ◽  
Object Localization ◽  
Feature Points ◽  
Video Frames ◽  
Novel Approach ◽  
Illumination Changes ◽  
Promising Solution

The emergence of video surveillance is the most promising solution for people living independently in their home. Recently several contributions for video surveillance have been proposed. However, a robust video surveillance algorithm is still a challenging task because of illumination changes, rapid variations in target appearance, similar nontarget objects in background, and occlusions. In this paper, a novel approach of object detection for video surveillance is presented. The proposed algorithm consists of various steps including video compression, object detection, and object localization. In video compression, the input video frames are compressed with the help of two-dimensional discrete cosine transform (2D DCT) to achieve less storage requirements. In object detection, key feature points are detected by computing the statistical correlation and the matching feature points are classified into foreground and background based on the Bayesian rule. Finally, the foreground feature points are localized in successive video frames by embedding the maximum likelihood feature points over the input video frames. Various frame based surveillance metrics are employed to evaluate the proposed approach. Experimental results and comparative study clearly depict the effectiveness of the proposed approach.

scholarly journals MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localization

2019 ◽  
Vol 33 ◽  
pp. 8851-8858 ◽  
Author(s):  
Zengyi Qin ◽  
Jinglu Wang ◽  
Yan Lu
Keyword(s):  
Depth Estimation ◽  
Geometric Reasoning ◽  
Object Localization ◽  
3D Object ◽  
Global Context ◽  
3D Space ◽  
3D Localization ◽  
Depth Dimension ◽  
Bounding Boxes ◽  
Rgb Image

Localizing objects in the real 3D space, which plays a crucial role in scene understanding, is particularly challenging given only a single RGB image due to the geometric information loss during imagery projection. We propose MonoGRNet for the amodal 3D object localization from a monocular RGB image via geometric reasoning in both the observed 2D projection and the unobserved depth dimension. MonoGRNet is a single, unified network composed of four task-specific subnetworks, responsible for 2D object detection, instance depth estimation (IDE), 3D localization and local corner regression. Unlike the pixel-level depth estimation that needs per-pixel annotations, we propose a novel IDE method that directly predicts the depth of the targeting 3D bounding box’s center using sparse supervision. The 3D localization is further achieved by estimating the position in the horizontal and vertical dimensions. Finally, MonoGRNet is jointly learned by optimizing the locations and poses of the 3D bounding boxes in the global context. We demonstrate that MonoGRNet achieves state-of-the-art performance on challenging datasets.

scholarly journals Triad system for object's 3D localization using low-resolution 2D ultrasonic sensor array

2020 ◽  
Vol 11 (2) ◽  
pp. 115-122
Author(s):  
Isam Abu-Qasmieh ◽  
Ali Mohammad Alqudah
Keyword(s):  
Sensor Array ◽  
Error Rates ◽  
Ultrasonic Sensor ◽  
Object Localization ◽  
Localization Algorithm ◽  
Low Resolution ◽  
3D Object ◽  
3D Space ◽  
3D Localization ◽  
Minimum Distances

AbstractIn the recently published researches in the object localization field, 3D object localization takes the largest part of this research due to its importance in our daily life. 3D object localization has many applications such as collision avoidance, robotic guiding and vision and object surfaces topography modeling. This research study represents a novel localization algorithm and system design using a low-resolution 2D ultrasonic sensor array for 3D real-time object localization. A novel localization algorithm is developed and applied to the acquired data using the three sensors having the minimum calculated distances at each acquired sample, the algorithm was tested on objects at different locations in 3D space and validated with acceptable level of precision and accuracy. Polytope Faces Pursuit (PFP) algorithm was used for finding an approximate sparse solution to the object location from the measured three minimum distances. The proposed system successfully localizes the object at different positions with an error average of ±1.4 mm, ±1.8 mm, and ±3.7 mm in x-direction, y-direction, and z-direction, respectively, which are considered as low error rates.

Sign in / Sign up

Export Citation Format

Share Document