scholarly journals Deep Deconvolution for Traffic Analysis with Distributed Acoustic Sensing Data

2021 ◽  
Author(s):  
Martijn van den Ende ◽  
André Ferrari ◽  
Anthony Sladen ◽  
Cédric Richard

Distributed Acoustic Sensing (DAS) is a novel vibration sensing technology that can be employed to detect vehicles and to analyse traffic flows using existing telecommunication cables. DAS therefore has great potential in future "smart city" developments, such as real-time traffic incident detection. Though previous studies have considered vehicle detection under relatively light traffic conditions, in order for DAS to be a feasible technology in real-world scenarios, detection algorithms need to also perform robustly under heavy traffic conditions. In this study we investigate the potential of roadside DAS for the simultaneous detection and characterisation of the velocity of individual vehicles. To improve the temporal resolution and detection accuracy, we propose a self-supervised Deep Learning approach that deconvolves the characteristic car impulse response from the DAS data, which we refer to as a Deconvolution Auto-Encoder (DAE). We show that deconvolution of the DAS data with our DAE leads to better temporal resolution and detection performance than the original (non-deconvolved) data. We subsequently apply our DAE to a 24-hour traffic cycle, demonstrating the feasibility of our proposed method to process large volumes of DAS data, potentially in near-real time.

2020 ◽  
Vol 104 (560) ◽  
pp. 235-240
Author(s):  
Leonard M. Wapner

Folded paper road maps are found next to sextants in the pile of obsolete navigation tools. GPS navigation apps like Waze and Google Maps, accurate to within a few metres, are available on all smartphones and most new cars. These apps provide drivers with real time traffic conditions and suggest minimum drive time routes, giving drivers the ability to avoid congestion and delays caused by heavy traffic, accidents, road construction and other hindrances.


2020 ◽  
Vol 7 (4) ◽  
pp. 667
Author(s):  
Gede Herdian Setiawan ◽  
I Ketut Dedy Suryawan

<p>Pertumbuhan jumlah kendaraan yang semakin meningkat setiap tahunnya mengakibatkan volume kendaraan yang melintasi ruas jalan semakin padat yang kerap mengakibatkan kemacetan lalu lintas. Kemacetan lalu lintas dapat menjadi beban biaya yang signifikan terhadap kegiatan ekonomi masyarakat. Informasi lalu lintas yang dinamis seperti informasi kondisi lalu lintas secara langsung <em>(real time)</em> akan membantu mempengaruhi aktivitas masyarakat pengguna lalu lintas untuk melakukan perencanaan dan penjadwalan aktivitas yang lebih baik. Penelitian ini mengusulkan model pengamatan kondisi lalu lintas berbasis data GPS pada <em>smartphone</em>, untuk informasi kondisi lalu lintas secara langsung. GPS <em>Receiver</em> pada <em>smartphone</em> menghasilkan data lokasi secara instan dan bersifat mobile sehingga dapat digunakan untuk pengambilan data kecepatan kendaraan secara langsung. Kecepatan kendaraan diperoleh berdasarkan jarak perpindahan koordinat kendaraan dalam satuan detik selanjutnya di konversi menjadi satuan kecepatan (km/jam) kemudian data kecepatan kendaraan di proses menjadi informasi kondisi lalu lintas. Secara menyeluruh model pengamatan berfokus pada tiga tahapan, yaitu akuisisi data kecepatan kendaraan berbasis GPS pada <em>smartphone</em>, pengiriman data kecepatan dan visualisasi kondisi lalu lintas berbasis GIS. Pengujian dilakukan pada ruas jalan kota Denpasar telah mampu mendapatkan data kecepatan kendaraan dan mampu menunjukkan kondisi lalu lintas secara langsung dengan empat kategori keadaan lalu lintas yaitu garis berwarna hitam menunjukkan lalu lintas macet dengan kecepatan kendaraan kurang dari 17 km/jam, merah menunjukkan padat dengan kecepatan kendaraan 17 km/jam sampai 27 km/jam, kuning menunjukkan sedang dengan kecepatan kendaraan 26 km/jam sampai 40 km/jam dan hijau menunjukkan lancar dengan kecepatan kendaraan diatas 40 km/jam.</p><p> </p><p><em><strong>Abstract</strong></em></p><p class="Abstract"><em>The growth in the number of vehicles that is increasing every year has resulted in the volume of vehicles crossing the road increasingly congested which often results in traffic congestion. Traffic congestion can be a significant cost burden on economic activities. Dynamic traffic information such as information on real time traffic conditions will help influence the activities of the traffic user community to better plan and schedule activities. This study proposes a traffic condition observation model based on GPS data on smartphones, for information on real time traffic conditions. The GPS Receiver on the smartphone produces location and coordinate data instantly and is mobile so that it can be used for direct vehicle speed data retrieval. Vehicle speed is obtained based on the displacement distance of the vehicle's coordinates in units of seconds and then converted into units of speed (km / h), the vehicle speed data is then processed into information on traffic conditions. Overall, the observation model focuses on three stages, namely GPS-based vehicle speed data acquisition on smartphones, speed data delivery and visualization of GIS-based traffic conditions. Tests carried out on the Denpasar city road segment have been able to obtain vehicle speed data and are able to show traffic conditions directly with four categories of traffic conditions, namely black lines indicating traffic jammed with vehicle speeds of less than 17 km / h, red indicates heavy with speed vehicles 17 to 27 km / h, yellow indicates medium speed with vehicles 26 km/h to 40 km / h and green shows fluent with vehicle speeds above 40 km / h.</em></p><p><em><strong><br /></strong></em></p>


2014 ◽  
Vol 6 ◽  
pp. 797293 ◽  
Author(s):  
Zhu Jiang ◽  
Shubin Li

According to the estimation information of dynamic traffic demands, a novel optimal control model of freeway was established on the basis of the hierarchical concept. There are four control modules in this model. The OD prediction module predicts the total traffic demands in a long time and determines the upper bound of the future queuing length in advance; the global optimal control module predicts the future traffic state and establishes the coordination constraints for each ramp in the network; the traffic demand estimation module estimates the real-time traffic conditions for each ramp; the local adaptive control module regulates ramp metering rate according to the estimated information of the real-time traffic conditions and the results optimized by the global optimal control module. The simulation results show that this control system is of a good dynamic performance. It coordinates the benefits of various ramps and optimizes the overall performance of the freeway network.


Author(s):  
Richard J. Hanowski ◽  
Susan C. Kantowitz ◽  
Barry H. Kantowitz

Human factors research can be used to design safe and efficient Advanced Traveler Information Systems (ATIS) that are easy to use (Kantowitz, Becker, & Barlow, 1993). This research used the Battelle Route Guidance Simulator (RGS) to examine two important issues related to driver behavior and acceptance of ATIS technology: (1) the effect of route familiarity on ATIS use and acceptance and (2) the level of information accuracy needed for an ATIS to be accepted and considered useful. The RGS included two 486 computers that provided drivers with real-time information and traffic reports. Drivers used a touch screen to select routes on one computer monitor and watched the results of their selection (i.e., real-time video of the traffic) on a second computer monitor. Drivers could use the system to obtain information about the traffic conditions on any link before traversing a route. In this experiment, subjects were exposed to four experimental conditions involving manipulation of the driver's familiarity with the route and the reliability of the traffic information obtained from the RGS (i.e., 100%, 71%, and 43% accuracy). The driver's goal was to reach the destination as quickly as possible by avoiding heavy traffic. The results indicated that drivers were able to benefit from system information when it was reliable, but not when it was unreliable. Trust ratings for the 43% accuracy group were significantly higher at the beginning of the four trials than at the end. Also, drivers were more apt to rely on the ATIS and accept information given in an unfamiliar traffic network versus a familiar one.


2021 ◽  
Vol 2021 ◽  
pp. 1-17
Author(s):  
Chunlin Xin ◽  
Lingjie Wang ◽  
Bin Liu ◽  
Yu-Hsi Yuan ◽  
Sang-Bing Tsai

Solid waste management and air pollution are two pressing issues in the functioning of large cities. This paper studies the optimization problem of the green transportation route of municipal solid waste and establishes a mathematical planning model based on real-time traffic conditions of the city and consideration of a time window and multiple transfer stations with the goal of minimizing energy consumption. In the optimal green transportation process in this paper, comprehensive consideration of vehicle speed, vehicle load, road gradient, and driving distance in different road sections based on real-time traffic conditions is incorporated, which has a better fuel-saving potential than the shortest path. A green transportation program can alleviate the air pollution problem in big cities and promote energy conservation and emission reduction in solid waste transportation.


2021 ◽  
Author(s):  
Rajeev Kumar ◽  
Pierre Bettinelli

Abstract During the evolution of the petroleum industry, surface seismic imaging has played a critical role in reservoir characterization. In the early days, borehole seismic (BHS) was developed to complement surface seismic. However, in the last few decades, a wide range of BHS surveys has been introduced to cater to new and unique objectives over the oilfield lifecycle. In the exploration phase, vertical seismic profiling (VSP) provides critical time-depth information to bridge time indexed subsurface images to log/reservoir properties in depth. This information can be obtained using several methods like conventional wireline checkshot or zero-offset vertical seismic profiling (ZVSP), seismic while drilling (SWD) or distributed acoustic sensing (DAS) techniques. SWD is a relatively new technique to record real-time data using tool deployed in the bottomhole assembly without disturbing the drilling. It helps to improve decision making for safer drilling especially in new areas in a cost-effective manner. Recently, a breakthrough technology, distributed acoustic sensing (DAS), has been introduced, where data are recorded using a fiber-optic cable with lots of saving. ZVSP also provides several parameters like, attenuation coefficient (Q), multiples prediction, impedance, reflectivity etc., which helps with characterizing the subsurface and seismic reprocessing. In the appraisal phase, BHS applications vary from velocity model update, anisotropy estimation, well- tie to imaging VSPs. The three-component VSP data is best suited for imaging and amplitude variation with offset (AVO) due to several factors like less noise interference due to quiet downhole environment, higher frequency bandwidth, proximity to the reflector, etc. Different type of VSP surveys (offset, walkaway, walkaround etc.) were designed to fulfill objectives like imaging, AVO, Q, anisotropy, and fracture mapping. In the development phase, high-resolution images (3D VSP, walkaway, or crosswell) from BHS surveys can assist with optimizing the drilling of new wells and, hence reduce costs. it can help with landing point selection, horizontal section placement, and refining interpretation for reserve calculation. BHS offers a wide range of surveys to assist the oilfield lifecycle during the production phase. Microseismic monitoring is an industry-known service to optimize hydraulic fracturing and is the only technique that captures the induced seismicity generated by hydraulic fracturing and estimate the fracture geometry (height, width, and azimuth) and in real time. During enhanced oil recovery (EOR) projects, BHS can be useful to optimize the hydrocarbon drainage strategies by mapping the fluid movement (CO2, water, steam) using time-lapse surveys like walkaway, 3D VSP and/or crosswell. DAS has brought a new dimension to provide vital information on injection or production evaluation, leak detection, flow behind tubing, crossflow diagnosis, and cement evaluation during production phase. This paper highlights the usage of BHS over the lifecycle of the oilfield.


IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 28137-28157 ◽  
Author(s):  
Sookyoung Lee ◽  
Mohamed Younis ◽  
Aiswarya Murali ◽  
Meejeong Lee

Author(s):  
JING CHEN ◽  
EVAN TAN ◽  
ZHIDONG LI

Traffic flow information can be employed in an intelligent transportation system to detect and manage traffic congestion. One of the key elements in determining the traffic flow information is traffic density estimation. The goal of traffic density estimation is to determine the density of vehicles on a given road from loop detectors, traffic radars, or surveillance cameras. However, due to the inflexibility of deploying loop detectors and traffic radars, there is a growing trend of using video-content-understanding technique to determine the traffic flow from a surveillance camera. But difficulties arise when attempting to do this in real-time under changing illumination and weather conditions as well as heavy traffic congestions. In this paper, we attempt to address the problem of real-time traffic density estimation by using a stochastic model called Hidden Markov Models (HMM) to probabilistically determine the traffic density state. Choosing a good set of model parameters for HMMs has a significant impact on the accuracy of traffic density estimation. Thus, we propose a novel feature extraction scheme to represent traffic density, and a novel approach to initialize and construct the HMMs by using an unsupervised clustering technique called AutoClass. We show through extensive experiments that our proposed real-time algorithm achieves an average traffic density estimation accuracy of 96.6% over various different illumination and weather conditions.


Sign in / Sign up

Export Citation Format

Share Document