Perspective Mapping Research Articles

System Integration of Sensor-Fusion Localization Tasks Using Vision-Based Driving Lane Detection and Road-Marker Recognition

This article proposes a vision-based perception system of using a monocular camera to detect the high-level features in the form of road markers and driving lanes for providing reliable visual measurements. Road markers and driving lanes are chosen because of their visually distinctive appearance compared to other objects as well as being easily annotated in the predefined digital map. For road-marker recognition, a template-matching-based method is applied to recognize the marker type and to estimate the corresponding position and orientation as well. For driving-lane detection, the proposed gradient orientation consistency combining the inverse perspective mapping spatial constraints is used to initialize the clearly visible lanes in the initial detection. Finally, the well-known particle filter is employed to integrate the visual information, inertial measurement unit (IMU), and global position system (GPS) data complementarily for correcting GPS errors. In particular, the lane measurement and road-marker measurement provide the lateral offset and relative position information, respectively, with respect to the ego vehicle. The IMU is used to estimate the dynamic behavior of the ego vehicle. The proposed vehicle localization system is evaluated in the real driving scenario of the standard campus environment within varying illumination conditions. The experiment results show that the lane-level localization accuracy is achieved by detecting road markers and driving lanes robustly.

Intellectual and Emotional Types of Homecoming

SummaryIn this article my aim is to outline a map of typologies of representations of home, seeking to illuminate the nature of the different issues contained therein, as well as the underlying feelings and mental mechanisms. I therefore try to draw a kind of categorical map of the diverse perspectives implied in the representation of home, or homecoming, or the quest for a home. I distinguish five levels as central categories of the homecoming: the mythical, the ontological-religious, the anthropological, the political, the psychic and pathological.

A Rapid Road Image Mosaic Method Based on Monocular Camera

As an important infrastructure, road has attracted a lot of attentions in recent years. Most of current road information extraction methods rely on either elaborate algorithms or complex equipment. This manuscript proposes a simple and rapid image mosaic method to extract road surface based on a monocular camera. First, key frames are extracted to remove redundant information from image sequences. To eliminate perspective effect, extracted key frames are transformed into top view of road images based on inverse perspective mapping algorithm with the help of an attitude tensor. Then, a coarse-to-fine registration strategy is proposed to align all transformed key frames into a unified coordinate system. Finally, considering the specificity of transformed images, a superposing and overlapping image fusion strategy is proposed to alleviate the effect of stitching seam. The experiments are conducted on a road with the size of 128×17 meters, and the experimental results demonstrate the effectiveness and efficiency of proposed method. In conclusion, the proposed method is simple, effective and efficient and can be applied in a wide range of applications such as large scale road surface diagnose.

(DCNN) Deep Convolution Neural Network Classifier and (EW-CSA) Earth Worm-Crow Search Algorithm for Lane Detection

Every year in India, most of the car accidents are occurs and affects on number of lives. Most of the road accidents are occurs due to driver’s inattention and fatigue. Drivers require to focus on different circumstances, together with vehicle speed and path, the separation between vehicles, passing vehicles, and potential risky or uncommon events ahead. Also the accident occurs due to the who bring into play cell phones at the same time as driving, drink and drive, etc. Due to this, most of the companies of automobiles tries to make available best Advanced Driver Assistance System (ADAS) to the customer to avoid the accidents. The lane detection approach is one of the method provided by automobile companies in ADAS, in which the vehicle must follows the lane. Therefore, there is less chance to get an accident. The information obtained from the lane is used to alert the driver. Therefore most of the researchers are attracted towards this field. But, due to the varying road circumstances, it is very difficult to detect the lane. The computer apparition and machine learning approaches are presents in most of the articles. In this article, we presents the deep learning scheme for identification of lane. There are two phases are presents in this work. In a first phase the image transformation is done and in second phase lane detection is occurred. At first, the proposed model gets the numerous lane pictures and changes the picture into its relating Bird's eye view picture by using Inverse perspective mapping transformation. The Deep Convolutional Neural Network (DCNN) classifier to identify the lane from the bird’s eye view image. The Earth Worm- Crow Search Algorithm (EW-CSA) is designed to help DCNN with the optimal weights. The DCNN classifier gets trained with the view picture from the bird’s eye image and the optimal weights are selected through newly developed EW-CSA algorithm. All these algorithms are performed in MATLAB. The simulation results shows that the exact detection of lane of road. Also, the accuracy, sensitivity, and specificity are calculated and its values are 0.99512, 0.9925, and 0.995 respectively.

Musical culture and the primary school: an investigation into parental attitudes to Whole Class Ensemble Teaching in the English primary school and potential impacts on children’s musical progress

AbstractMusical cultures in primary schools are influenced by motivators which include intrinsic and extrinsic factors. Whole Class Ensemble Teaching (WCET) as realised through provision from Music Education Hubs in England is an extrinsic factor which has been widely influential. This article explores the dynamics in play in parental engagement in music provision, as realised through domains of musical value and progression in the context of WCET provision. It presents research, based on data from one primary school in the English Midlands, drawing on responses from children, parents, the WCET teacher and the head teacher of the school. The research used semi-structured interviews and graphical elicitation as research methodologies to create a conceptual map of theoretical perspectives for parental responses to WCET and suggests that triangulating motivating influences from parents, WCET and learners remain an emergent domain.

Counting crowds using a scale-distribution-aware network and adaptive human-shaped kernel

Intelligent bus system plays a key role in the modern smart city. The number of passengers in the buses or at the stations is necessary for making an optimal scheduling policy of public buses. We develop a crowd counting algorithm to provide the counting information for a bus dispatch system in a human–machine system. In consideration of the challenges (e.g., pedestrian occlusions, non-uniform crowd distributions, and scale variations) existed in hand-crafted features based crowd counting, a scale-distribution-aware multi-column convolutional neural network (SDA-MCNN) is presented to count crowds by summing up the output (denoted as the density map) of the SDA-MCNN. The SDA-MCNN is robust to scale variations by processing a crowd image with multiple convolutional neural network (CNN) columns and minimizing the per-scale loss. A weighted Euclidean loss is proposed to handle non-uniform crowd distributions. The loss can increase activations in dense regions and restrain activations in backgrounds. A new approach to estimate perspective maps of dense crowds is put forward to offer necessary information for generating density maps with human-shaped kernels. Evaluations on benchmarks are performed with other state-of-the-art counting approaches using deep neural networks. Comparative results verify the accuracy of our counting approach in challenging crowds. Evaluations on the real world BUS data reveal the accuracy of the proposed approach in counting passengers in spite of the complex environment.

PENERAPAN KONSEP BALANCED SCORECARD DALAM PENGUKURAN KINERJA INSTANSI PEMERINTAH PADA INSTITUT PEMERINTAHAN DALAM NEGERI

Performance in the public sector is multidimensional and comprehensive, so that the nature of output produced by the public sector is more intangible output, so to measure the performance of the public sector it is necessary to choose a comprehensive performance measurement technique that is the Balanced Scorecard.
 Research Objectives to describe the application of each Balanced Scorecard perspective in measuring agency performance. The research method used is descriptive qualitative method.
 IPDN is a public sector organization with a main focus on output that is "producing competent, character and personality cadres of government" which ultimately to serve and improve the welfare of the community. Thus the need for innovative development in implementing a comprehensive organizational performance measurement system that can be implemented by the work unit in measuring the performance of agencies as outlined in the Government Agency Performance Report.
 The concept of the Balanced Scorecard is integrated into the IPDN Strategic map and then mapped in the perspective mapping matrix, indicators, weights, and sources of measurement data, so that formulations for Organizational Performance Values ​​can be identified. The modification of the Balanced Scorecard method applied by IPDN agencies includes 4 (four) perspectives namely Customer & stakeholders perspective, Financial perspective, Internal business process perspective, and Learning and Growth perspective. Keywords: Balanced Scorecard, Strategic map, performance

Measurement of harvesting width of intelligent combine harvester by improved probabilistic Hough transform algorithm

Aiming at the problem that the harvesting width measurement of rice or wheat is susceptible to interference and poor real-time performance, an improved probabilistic Hough transform (PHT) width measurement algorithm based on morphological vertical line extraction is proposed. Inverse perspective mapping (IPM) restores the parallel relationship of the vertical line of the three-dimensional world. Image enhancement of the object region is used to highlight differences between the harvested and unharvested region. The median filter of large size filter window eliminates the interference of local noise. Improved PHT based on the vertical line extraction of the threshold segmentation realizes the real-time accurate measurement of the harvesting width during the operation of the intelligent combine harvester. Experiments demonstrate that the improved PHT can accurately obtain the harvesting width error of not more than 64 mm at an average success rate of 96.025%, and can measure the harvesting width in real time at 77.675 ms/frame.

Efficient Vehicle Detection and Distance Estimation Based on Aggregated Channel Features and Inverse Perspective Mapping from a Single Camera

In this paper a method for detecting and estimating the distance of a vehicle driving in front using a single black-box camera installed in a vehicle was proposed. In order to apply the proposed method to autonomous vehicles, it was required to reduce the throughput and speed-up the processing. To do this, the proposed method decomposed the input image into multiple-resolution images for real-time processing and then extracted the aggregated channel features (ACFs). The idea was to extract only the most important features from images at different resolutions symmetrically. A method of detecting an object and a method of estimating a vehicle’s distance from a bird’s eye view through inverse perspective mapping (IPM) were applied. In the proposed method, ACFs were used to generate the AdaBoost-based vehicle detector. The ACFs were extracted from the LUV color, edge gradient, and orientation (histograms of oriented gradients) of the input image. Subsequently, by applying IPM and transforming a 2D input image into 3D by generating an image projected in three dimensions, the distance between the detected vehicle and the autonomous vehicle was detected. The proposed method was applied in a real-world road environment and showed accurate results for vehicle detection and distance estimation in real-time processing. Thus, it was showed that our method is applicable to autonomous vehicles.

Multiple Lanes Identification for Advanced Driver Assistance System (ADAS)

Now a days, a multi-lane recognition technique that uses the ridge features and the inverse perspective mapping (IPM) is generally used to distinguish lanes since it can evacuate the perspective distortion on lines that lie in parallel in reality. The lane detection is one of the approach to design the ADAS, if the vehicles follows the lane then there is less chance to get an accident. The detected information of lane path is used for controlling the vehicles and giving alerts to drivers. Therefore most of the researchers are attracted towards this field. But, due to the varying road conditions, it is very difficult to detect the lane. The computer vision and machine learning approaches are presents in most of the articles. In this paper, a survey of different method is presents for the road picture segmentation for the multi-lane detection. The Lane Departure Warning (LDW) system can help to reduce vehicle crashes that are caused by careless or drowsy driving. There has been much research on vision based lane detection for the LDW system. In these lane detection methods, color or edge information is utilized as a feature of the lane. The feature-based methods are usually applied to localize the lanes in the road images by extracting low-level features. On the other hand, the model-based methods use several geometrical elements to describe the lanes, including parabolic curves, hyperbola and straight lines. Feature-based methods require a dataset containing several thousand images of the roads with well-painted and prominent lane markings that are subsequently converted to features. Moreover, these methods may suffer from noise.

Computer Vision Measurement of Pointer Meter Readings Based on Inverse Perspective Mapping

A computer vision method for measuring multiple pointer meters is proposed based on the inverse perspective mapping. First, the measured meter scales are used as the calibration objects to obtain the extrinsic parameters of the meter plane. Second, normal vector of the meter plane can be acquired by the extrinsic parameters, obtaining the rotation transformation matrix of the meter image. Then, the acquired meter image is transformed to a position both parallel to the meter plane and near the main point by the rotation transformation matrix and the extrinsic parameters, eliminating the perspective effect of the acquired image. Finally, the transformed image is tested by the visual detection method to obtain the readings of the pointer meter, improving measurement precision. The results of the measurement verify the effectiveness and accuracy of the method.

On the Image Sensor Processing for Lane Detection and Control in Vehicle Lane Keeping Systems.

Lane keeping systems for a keeping a vehicle in the desired lane is key to advanced driving assistance system in autonomous vehicles. This paper presents a cost-effective image sensor with efficient processing algorithm for lane detection and lane control applications to autonomous delivery systems. The algorithm includes (1) lane detection by inverse perspective mapping and random sample consensus parabola fitting and (2) lane control by pure pursuit steering controller and classical proportional integral speed controller based on a nonholonomic kinematic model. The image sensor experiments conducted on a 1/10 scale model car maneuvering in a straight–curve–straight lane validate the better processing performance before, during, and after the turning section over previous work. The image sensor with the processing algorithm achieves the average lane detection error within 5% and maximum cross-track error within 9% in real-time. The development shall pave the way to cost-effective autonomous delivery systems.

Robust lane‐detection algorithm based on improved symmetrical local threshold for feature extraction and inverse perspective mapping

Here, an extended version of the symmetrical local threshold (SLT) algorithm is introduced for lane feature extraction and used in a novel lane-detection system. The introduced feature map extractor utilises parallel lane border features as well as the dark-light-dark (DLD) pattern of the lane marking used in SLT. Hence, compared to the SLT, the true positive to positive rate of the calculated feature maps is increased from 69% to 86% on the ROMA dataset. In addition, the proposed algorithm supplies orientation information for the estimated feature points, which can be useful for many optimisation algorithms. Consequently, based on the estimated lane feature orientations, a global lane orientation is calculated and used for both enhancing the feature map and estimating a one-dimensional (1D) lateral offset likelihood function. Then, the estimated 1D functions are filtered temporally and up to two linear lane candidates are detected. For increased flexibility, robust fitting is applied to the feature points in the region of interest (ROI). Finally, based on the detection of the previous frame, a mask is created and applied to the next frame. When tested on 2301 road images, mean error in lateral offset is calculated as 4.1 pixel on the IPM images.

Evaluating the effect of MIPM on vehicle detection performance

ABSTRACTThe introduction of new techniques to improve the robustness and accuracy of vehicle detection is always important for the intelligent transportation system as it may face different problems and challenges. Conventional image-based vehicle detection methods have presented difficulties in acquiring good images due to perspective and background noise, poor lighting and weather conditions. We propose a high-accurate, vehicle detection method by using Modified Inverse Perspective Mapping. Thus, the perspective effect is removed, and then the Hough transform was applied to extract road lines and lanes. Gaussian Mixture Model and chromaticity-based strategy were applied to segment the moving vehicles and tackle shadow effects, respectively. We evaluated the performance of the proposed method under recorded videos in Madrid and Tehran (with different weather conditions at urban and interurban areas). Results indicate that the proposed approach is feasible, and more accurate compared to others, especially when facing bad weather conditions and lighting variations in different environments.

Robust obstacle detection for advanced driver assistance systems using distortions of inverse perspective mapping of a monocular camera

This paper presents a robust method for generic obstacle detection and collision warning in Advanced Driver Assistance Systems (ADAS). The highlight of our method is the ability to detect all obstacles without prior knowledge and detect partially occluded obstacles including the obstacles that have not completely appeared in the frame (truncated obstacles). Our results show an improvement of 90% more true positives per frame compared to one of the state-of-the-art methods. Our proposed method is robust to variations in illumination and to a wide variety of vehicles and obstacles that are encountered while driving. Distortions are introduced when Inverse Perspective Mapping (IPM) projects the camera image onto the road surface plane. In this paper, we first show that the angular distortion in the IPM domain belonging to obstacle edges varies as a function of their corresponding 2D location in the camera plane. We use this information to perform proposal generation. We propose a novel proposal assessment method based on fusing statistical properties from both the IPM image and the camera image to perform robust outlier elimination and false positive reduction. We also present an annotated obstacle detection dataset derived from various source videos that can serve as a benchmark for the evaluation of future obstacle detection algorithms. The source videos containing diverse illumination and traffic conditions are derived from multiple publicly available datasets.

Scene invariant crowd counting using multi‐scales head detection in video surveillance

With a soaring increase in the application of video surveillance in daily life, the estimation of crowd density has already become a hot field. Crowd counting has a very close relationship with traffic planning, pedestrian analysing and emergency warning. Here, a novel crowd counting method based on multi-scales head detection is proposed. The authors' approach first uses gradients difference to extract the foreground of the images and apply the overlapped patches in different scales to split the input images. Then, the patches are selected and classified into different groups corresponding to their gradient distributions, and features are extracted for training. Finally, with the predicting result, density maps of different scales are computed and summed with the perspective map. In particular, the authors' method overcomes the traditional detecting method's deficiencies of low accuracy when facing perspective transformation. Also, experiments demonstrate that this proposed method not only achieved high accuracy in counting but also has outstanding robustness in our data sets.

A robust lane detection method based on hyperbolic model

Lane detection is an essential part of safety assurance in intelligent vehicle and advanced driver assistance systems. Despite many methods having been proposed, there still remain challenges such as complex road surface and large curvature. In this paper, we present a robust lane detection method under structured roads to solve these issues. The method contains two parts: straight line detection in near field and curve matching in far field. Instead of generating top-view image by inverse perspective mapping (IPM), we propose a new form of IPM application to reduce noise that we only take advantage of sub-pixel-level spatial relations and project line segments obtained by line segments detector to top-view image. Then, we apply density-based spatial clustering of applications with noise to clustering segments and design a fusion method to extract the optimal lines combination from clusters. Finally, a weighted hyperbolic model is proposed to finish curve fitting. The results of experiment indicate that the method has robust performance in complex environment.

Situation-dependent remote AR collaborations: Image-based collaboration using a 3D perspective map and live video-based collaboration with a synchronized VR mode

The development of the Internet and smart devices has made it possible to support remote collaborations, which allows the expert and the worker to share information and co-work together in various and dispersed industrial fields. However, collaborations that exchange only audio and video information have limitations in the guided instruction of tasks, training of workers, and understanding of the situation. As augmented reality (AR) technology is considered to provide a more intuitive and immersive visualization and interaction in physical workspaces, many research works have been conducted to integrate AR into remote collaboration. Usually, there are two different types of AR collaboration depending on the shared media: 1) image-based AR collaboration and 2) live video-based AR collaboration. However, most of the previous research works cannot effectively support not only visual augmentation suitable for the situation but also accurate and effective annotations in the shared AR space. In this paper, we propose a situation-dependent remote AR collaboration approach that can selectively support either image- or live video-based AR collaborations: 1) image-based AR collaboration using a 3D perspective map and 2) live video-based AR collaboration with a synchronized VR mode. In particular, in the case of a certain situation with a limited network connection or limited HW/SW capabilities of the smart device, the image-based AR collaboration is more preferred. However, existing approaches cannot provide an integrated AR space from shared images. The proposed image-based AR collaboration enables to construct a 3D perspective map from the shared images taken in three or more directions, which can provide an integrated AR space for more effective AR annotations for remote collaboration. In the case of a normal situation without such problems, the live video-based AR collaboration should be supported. However, previous works have inherent problems such as inaccurate and mismatched AR annotations when the viewpoint of the live video is changed. The proposed live video-based AR collaboration with a synchronized VR mode can provide more effective and accurate 3D annotations by synchronizing virtual objects with physical objects. In particular, the VR mode can provide a complementing VR view of the AR-based physical space. In addition, through quantitative and qualitative experimental evaluation, we have conducted comparative studies with previous works. The results of this research show that the approach presented in this research has higher qualitative evaluation such as human behavior and task usability, as well as higher quantitative evaluation such as task performance and accuracy. Therefore, it is expected that the proposed approach can provide more user-oriented collaboration that considers user's situation and device performance in various industrial applications.

Image-Based Lateral Position, Steering Behavior Estimation, and Road Curvature Prediction for Motorcycles

This letter presents an image-based approach to simultaneously estimate the lateral position of a powered-two-wheeled vehicle on the road, its steering behavior and predict the road curvature ahead of the motorcycle. This letter is based on the inverse perspective mapping technique combined with a road lanes detection algorithm capable of detecting straight and curved lanes. Then, a clothoid model is used to extract pertinent information from the detected road markers. Finally, the performance of the proposed approach is illustrated through simulations carried out with the well-known motorcycle simulator “BikeSim.” The results are very promising since the algorithm is capable of estimating, in real time, the road geometry and the vehicle location with a better accuracy than the one given by the commercial GPS.

Application of Inverse Perspective Mapping for Advanced Driver Assistance Systems in Automotive Embedded Systems

<span style="font-size: 9.0pt; font-family: 'Times New Roman','serif'; mso-fareast-font-family: 'Times New Roman'; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: AR-SA; mso-bidi-font-weight: bold;">In the recent times vehicle manufactures and automotive suppliers are progressing towards building vision based subsystems for provisioning driver assistance while targeting the automotive safety critical needs. While the acquired images constitute the fundamental input for any vision based system, transforms on images become essential to derive and gain insight into certain specific features. These derived features are used and reused at multiple places for varied automotive applications. This situation warrants a scalable and flexible image processing platform for a class of automotive applications. An attempt is made in this Research work to propose architecture that, specially, includes a layer of image transformations and to implement a prototype image processing platform. Inverse Perspective Mapping (IPM), a widely used class of transforms is emphasized in the present architecture alongside other nominal transforms. Lane departure warning system is implemented on this platform for the purpose of illustration and to analyze the effectiveness of the proposed architecture</span>