A Sensor-Based Visual Effect Evaluation of Chevron Alignment Signs’ Colors on Drivers through the Curves in Snow and Ice Environment

Chen

IET Intelligent Transport Systems

et al. 2019

In this paper, we present a testbed platform for realizing cooperative adaptive cruise control (CACC) enabled by LTE-V (LTE-vehicle). The platform is developed on a platoon of vehicles, each of which is equipped with a suite of on-board sensing and computing devices for environment perception and automated vehicle control, as well as an LTE-V transceiver for high-performance vehicle-to-vehicle (V2V) communication. The hardware architecture and software architecture, especially the perception and control methods, of the platform are described. Field experiments in different road conditions are conducted to verify the feasibility of our platform. The results also show the potential of V2V communications via LTE-V in terms of improving the sensing capability of individual vehicle's on-board sensors.2 information (e.g., speed, wheel angle, heading and location, throttle and brake actions, etc.) to achieve better environment perception, has attracted wide research attentions. The dedicated short-range communications (DSRC) technology has been considered as the solution to realizing V2X communication for years. The US Federal Communication Commission (FCC) has allocated a 75 MHz spectrum in the 5.9 GHz band for DSRC [25]. The information exchanged among vehicles can be encoded into Basic Safety Message (BSM) and periodically broadcasted by vehicles according to the Society of Automotive Engineering (SAE) standard [26]. However, due to the ad hoc working nature, DSRC may not be able to fully guarantee highly-reliable and low-delay communication in all traffic conditions.In the past few years, the cellular-based LTE-V (LTE vehicle) technology [27] has started to be investigated in many countries and research communities. For example, a data exchange standard [28] is currently being developed by the Society of Automotive Engineers of China (SAE-China). Cooperative automated driving is seen as one of the most important use cases supported by LTE-V and LTE-eV2X (the next generation of LTE-V) according to 3GPP TR 22.886 [29]. LTE-V supports both V2V (vehicle-to-vehicle) communication over the peer-to-peer PC5 interface, and V2N (vehicle-to-network) communication over the LTE-Uu interface. Therefore, the interference management and scheduling of V2V communication traffic can be assisted by base stations to obtain a more reliable and efficient message dissemination compared with DSRC, especially in the highly mobile environment. The transmission delay of LTE-V is expected to be about 25ms through V2V direct communication, which meets the latency requirements of platooning defined in 3GPP TR 22.886. A comparative analysis between LTE-V and DSRC [30] is shown in Table 1, which clearly demonstrates the advantages of the former technology.

Section: Fig 1 a Platoon Of Vehicles On The Roadmentioning

confidence: 99%

Development and verification of cooperative adaptive cruise control via LTE‐V

Chen

IET Intelligent Transport Systems

et al. 2019

“…Bale detection challenges: When it comes to object detection, associated methods are commonly sensitive to the illumination and object and background domain change. A non-robust model can easily fail if it was not taking into account the variation in light conditions [16,17]. Because of the diversity of illumination situations, seasons, and weather conditions, object detection in the outdoor environment is more complicated than in the indoor environment, since humans can manipulate a consistent environment, as is shown in Table 1.…”

Section: Introductionmentioning

confidence: 99%

Augmenting Crop Detection for Precision Agriculture with Deep Visual Transfer Learning—A Case Study of Bale Detection

Zhao

Yamada

et al. 2020

Remote Sensing

Self Cite

In recent years, precision agriculture has been researched to increase crop production with less inputs, as a promising means to meet the growing demand of agriculture products. Computer vision-based crop detection with unmanned aerial vehicle (UAV)-acquired images is a critical tool for precision agriculture. However, object detection using deep learning algorithms rely on a significant amount of manually prelabeled training datasets as ground truths. Field object detection, such as bales, is especially difficult because of (1) long-period image acquisitions under different illumination conditions and seasons; (2) limited existing prelabeled data; and (3) few pretrained models and research as references. This work increases the bale detection accuracy based on limited data collection and labeling, by building an innovative algorithms pipeline. First, an object detection model is trained using 243 images captured with good illimitation conditions in fall from the crop lands. In addition, domain adaptation (DA), a kind of transfer learning, is applied for synthesizing the training data under diverse environmental conditions with automatic labels. Finally, the object detection model is optimized with the synthesized datasets. The case study shows the proposed method improves the bale detecting performance, including the recall, mean average precision (mAP), and F measure (F1 score), from averages of 0.59, 0.7, and 0.7 (the object detection) to averages of 0.93, 0.94, and 0.89 (the object detection + DA), respectively. This approach could be easily scaled to many other crop field objects and will significantly contribute to precision agriculture.

“…Various techniques and methods of detecting overtaking have been researched. The works of [26,27] have promoted a system that used GPS and phones to detect acceleration and deceleration to estimate the congestion. A mixed algorithm was created to detect the acceleration, combining dynamic planning with robust information [28].…”

Section: Introductionmentioning

confidence: 99%

Real-Time Vehicle Motion Detection and Motion Altering for Connected Vehicle: Algorithm Design and Practical Applications

Zhao

Yin

et al. 2019

Sensors

Self Cite

Real-time capturing of vehicle motion is the foundation of connected vehicles (CV) and safe driving. This study develops a novel vehicle motion detection system (VMDS) that detects lane-change, turning, acceleration, and deceleration using mobile sensors, that is, global positioning system (GPS) and inertial ones in real-time. To capture a large amount of real-time vehicle state data from multiple sensors, we develop a dynamic time warping based algorithm combined with principal component analysis (PCA). Further, the designed algorithm is trained and evaluated on both urban roads and highway using an Android platform. The aim of the algorithm is to alert adjacent drivers, especially distracted drivers, of potential crash risks. Our evaluation results based on driving traces, covering over 4000 miles, conclude that VMDS is able to detect lane-change and turning with an average precision over 76% and speed, acceleration, and brake with an average precision over 91% under the given testing data dataset 1 and 4. Finally, the alerting tests are conducted with a simulator vehicle, estimating the effect of alerting back or front vehicle the surrounding vehicles’ motion. Nearly two seconds are gained for drivers to make a safe operation. As is expected, with the help of VMDS, distracted driving decreases and driving safety improves.