scholarly journals Lane-level localization system using surround-view cameras adaptive to different driving conditions

2020 ◽  
Vol 17 (2) ◽  
pp. 172988142092163
Author(s):  
Tianyi Li ◽  
Yuhan Qian ◽  
Arnaud de La Fortelle ◽  
Ching-Yao Chan ◽  
Chunxiang Wang
Keyword(s):  
Deep Learning ◽  
Low Cost ◽  
Lateral Position ◽  
Measurement Unit ◽  
Map Matching ◽  
Matching Model ◽  
Localization System ◽  
Perceptual Model ◽  
Road Map ◽  
Driving Conditions

This article presents a lane-level localization system adaptive to different driving conditions, such as occlusions, complicated road structures, and lane-changing maneuvers. The system uses surround-view cameras, other low-cost sensors, and a lane-level road map which suits for mass deployment. A map-matching localizer is proposed to estimate the probabilistic lateral position. It consists of a sub-map extraction module, a perceptual model, and a matching model. A probabilistic lateral road feature is devised as a sub-map without limitations of road structures. The perceptual model is a deep learning network that processes raw images from surround-view cameras to extract a local probabilistic lateral road feature. Unlike conventional deep-learning-based methods, the perceptual model is trained by auto-generated labels from the lane-level map to reduce manual effort. The matching model computes the correlation between the sub-map and the local probabilistic lateral road feature to output the probabilistic lateral estimation. A particle-filter-based framework is developed to fuse the output of map-matching localizer with the measurements from wheel speed sensors and an inertial measurement unit. Experimental results demonstrate that the proposed system provides the localization results with submeter accuracy in different driving conditions.

scholarly journals A Novel Vehicle Stationary Detection Utilizing Map Matching and IMU Sensors

2014 ◽  
Vol 2014 ◽  
pp. 1-13 ◽  
Author(s):  
Md. Syedul Amin ◽  
Mamun Bin Ibne Reaz ◽  
Salwa Sheikh Nasir ◽  
Mohammad Arif Sobhan Bhuiyan ◽  
Mohd. Alauddin Mohd. Ali
Keyword(s):  
Stationary State ◽  
Navigation System ◽  
Urban Areas ◽  
Microelectromechanical Systems ◽  
Low Cost ◽  
Measurement Unit ◽  
Map Matching ◽  
Mm Algorithm ◽  
Bias Drift ◽  
Navigation Information

Precise navigation is a vital need for many modern vehicular applications. The global positioning system (GPS) cannot provide continuous navigation information in urban areas. The widely used inertial navigation system (INS) can provide full vehicle state at high rates. However, the accuracy diverges quickly in low cost microelectromechanical systems (MEMS) based INS due to bias, drift, noise, and other errors. These errors can be corrected in a stationary state. But detecting stationary state is a challenging task. A novel stationary state detection technique from the variation of acceleration, heading, and pitch and roll of an attitude heading reference system (AHRS) built from the inertial measurement unit (IMU) sensors is proposed. Besides, the map matching (MM) algorithm detects the intersections where the vehicle is likely to stop. Combining these two results, the stationary state is detected with a smaller timing window of 3 s. A longer timing window of 5 s is used when the stationary state is detected only from the AHRS. The experimental results show that the stationary state is correctly identified and the position error is reduced to 90% and outperforms previously reported work. The proposed algorithm would help to reduce INS errors and enhance the performance of the navigation system.

scholarly journals A Real Time Localization System for Vehicles Using Terrain-Based Time Series Subsequence Matching

2020 ◽  
Vol 12 (16) ◽  
pp. 2607
Author(s):  
Hongjuan Zhang ◽  
Wenzhuo Li ◽  
Chuang Qian ◽  
Bijun Li
Keyword(s):  
Time Series ◽  
Real Time ◽  
Urban Areas ◽  
Position Estimation ◽  
Global Navigation Satellite Systems ◽  
Measurement Unit ◽  
Subsequence Matching ◽  
Filter Model ◽  
Localization System ◽  
Road Map

Global Navigation Satellite Systems (GNSSs) are commonly used for positioning vehicles in open areas. Yet a GNSS frequently encounters loss of lock in urban areas. This paper presents a new real-time localization system using measurements from vehicle odometer data and data from an onboard inertial measurement unit (IMU), in the case of lacking GNSS information. A Dead Reckoning model integrates odometer data, IMU angular and velocity data to estimate the rough position of the vehicle. We then use an R-Tree structured reference road map of pitch data to boost spatial search efficiency. An optimized time series subsequence matching method matches the measured pitch data and the stored pitch data in reference road map for more accurate position estimation. The two estimated positions are fused using an extended Kalman filter model for final localization. The proposed localization system was tested for computational complexity with a median runtime of 12 ms, and for positioning accuracy with a median position error of 0.3 m.

Developing an Artificial Intelligence Project in your Radiology Department

2020 ◽  
Vol 2 ◽  
pp. 58-61 ◽  
Author(s):  
Syed Junaid ◽  
Asad Saeed ◽  
Zeili Yang ◽  
Thomas Micic ◽  
Rajesh Botchu
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Health Care ◽  
Deep Learning ◽  
Learning Algorithms ◽  
Radiology Department ◽  
Short Article ◽  
Computing Power ◽  
Road Map ◽  
Key Concepts

The advances in deep learning algorithms, exponential computing power, and availability of digital patient data like never before have led to the wave of interest and investment in artificial intelligence in health care. No radiology conference is complete without a substantial dedication to AI. Many radiology departments are keen to get involved but are unsure of where and how to begin. This short article provides a simple road map to aid departments to get involved with the technology, demystify key concepts, and pique an interest in the field. We have broken down the journey into seven steps; problem, team, data, kit, neural network, validation, and governance.

scholarly journals Application of Deep Learning in Integrated Pest Management: A Real-Time System for Detection and Diagnosis of Oilseed Rape Pests

2019 ◽  
Vol 2019 ◽  
pp. 1-14 ◽  
Author(s):  
Yong He ◽  
Hong Zeng ◽  
Yangyang Fan ◽  
Shuaisheng Ji ◽  
Jianjian Wu
Keyword(s):  
Deep Learning ◽  
Integrated Pest Management ◽  
Pest Management ◽  
Real Time ◽  
Oilseed Rape ◽  
Data Augmentation ◽  
Low Cost ◽  
Response Speed ◽  
Original Model ◽  
Real Time System

In this paper, we proposed an approach to detect oilseed rape pests based on deep learning, which improves the mean average precision (mAP) to 77.14%; the result increased by 9.7% with the original model. We adopt this model to mobile platform to let every farmer able to use this program, which will diagnose pests in real time and provide suggestions on pest controlling. We designed an oilseed rape pest imaging database with 12 typical oilseed rape pests and compared the performance of five models, SSD w/Inception is chosen as the optimal model. Moreover, for the purpose of the high mAP, we have used data augmentation (DA) and added a dropout layer. The experiments are performed on the Android application we developed, and the result shows that our approach surpasses the original model obviously and is helpful for integrated pest management. This application has improved environmental adaptability, response speed, and accuracy by contrast with the past works and has the advantage of low cost and simple operation, which are suitable for the pest monitoring mission of drones and Internet of Things (IoT).

scholarly journals Biomechanics of Trail Running Performance: Quantification of Spatio-Temporal Parameters by Using Low Cost Sensors in Ecological Conditions

2021 ◽  
Vol 11 (5) ◽  
pp. 2093
Author(s):  
Noé Perrotin ◽  
Nicolas Gardan ◽  
Arnaud Lesprillier ◽  
Clément Le Goff ◽  
Jean-Marc Seigneur ◽  
...  
Keyword(s):  
Heart Rate ◽  
Low Cost ◽  
Step Length ◽  
Measurement Unit ◽  
Ecological Conditions ◽  
Sports Science ◽  
Ground Contact Time ◽  
Spatio Temporal ◽  
Performance Results ◽  
Trail Running

The recent popularity of trail running and the use of portable sensors capable of measuring many performance results have led to the growth of new fields in sports science experimentation. Trail running is a challenging sport; it usually involves running uphill, which is physically demanding and therefore requires adaptation to the running style. The main objectives of this study were initially to use three “low-cost” sensors. These low-cost sensors can be acquired by most sports practitioners or trainers. In the second step, measurements were taken in ecological conditions orderly to expose the runners to a real trail course. Furthermore, to combine the collected data to analyze the most efficient running techniques according to the typology of the terrain were taken, as well on the whole trail circuit of less than 10km. The three sensors used were (i) a Stryd sensor (Stryd Inc. Boulder CO, USA) based on an inertial measurement unit (IMU), 6 axes (3-axis gyroscope, 3-axis accelerometer) fixed on the top of the runner’s shoe, (ii) a Global Positioning System (GPS) watch and (iii) a heart belt. Twenty-eight trail runners (25 men, 3 women: average age 36 ± 8 years; height: 175.4 ± 7.2 cm; weight: 68.7 ± 8.7 kg) of different levels completed in a single race over a 8.5 km course with 490 m of positive elevation gain. This was performed with different types of terrain uphill (UH), downhill (DH), and road sections (R) at their competitive race pace. On these sections of the course, cadence (SF), step length (SL), ground contact time (GCT), flight time (FT), vertical oscillation (VO), leg stiffness (Kleg), and power (P) were measured with the Stryd. Heart rate, speed, ascent, and descent speed were measured by the heart rate belt and the GPS watch. This study showed that on a ≤10 km trail course the criteria for obtaining a better time on the loop, determined in the test, was consistency in the effort. In a high percentage of climbs (>30%), two running techniques stand out: (i) maintaining a high SF and a short SL and (ii) decreasing the SF but increasing the SL. In addition, it has been shown that in steep (>28%) and technical descents, the average SF of the runners was higher. This happened when their SL was shorter in lower steep and technically challenging descents.

scholarly journals Computational Complexity Reduction of Neural Networks of Brain Tumor Image Segmentation by Introducing Fermi–Dirac Correction Functions

Entropy ◽  
2021 ◽  
Vol 23 (2) ◽  
pp. 223
Author(s):  
Yen-Ling Tai ◽  
Shin-Jhe Huang ◽  
Chien-Chang Chen ◽  
Henry Horng-Shing Lu
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Computational Complexity ◽  
High Performance ◽  
Low Cost ◽  
Structural Complexity ◽  
Correction Function ◽  
Computational Time ◽  
Learning Methods ◽  
Band Theory

Nowadays, deep learning methods with high structural complexity and flexibility inevitably lean on the computational capability of the hardware. A platform with high-performance GPUs and large amounts of memory could support neural networks having large numbers of layers and kernels. However, naively pursuing high-cost hardware would probably drag the technical development of deep learning methods. In the article, we thus establish a new preprocessing method to reduce the computational complexity of the neural networks. Inspired by the band theory of solids in physics, we map the image space into a noninteraction physical system isomorphically and then treat image voxels as particle-like clusters. Then, we reconstruct the Fermi–Dirac distribution to be a correction function for the normalization of the voxel intensity and as a filter of insignificant cluster components. The filtered clusters at the circumstance can delineate the morphological heterogeneity of the image voxels. We used the BraTS 2019 datasets and the dimensional fusion U-net for the algorithmic validation, and the proposed Fermi–Dirac correction function exhibited comparable performance to other employed preprocessing methods. By comparing to the conventional z-score normalization function and the Gamma correction function, the proposed algorithm can save at least 38% of computational time cost under a low-cost hardware architecture. Even though the correction function of global histogram equalization has the lowest computational time among the employed correction functions, the proposed Fermi–Dirac correction function exhibits better capabilities of image augmentation and segmentation.

Sign in / Sign up

Export Citation Format

Share Document