Test Results and Validation of the FeedMAP Framework with ADAS Applications

<div class="htmlview paragraph">Digital maps have large potential to enhance or enable Advanced Driver Assistance Systems (ADAS) by extending driver horizon and therefore to contribute to safer, smarter and cleaner road transport. As a predictive sensor called ADAS Horizon, in-vehicle digital maps are an important source of information providing look-ahead capability for ADAS applications and providing further information for on-board sensors to enhance environment perception.</div> <div class="htmlview paragraph">This paper reports on results from the European Commission project MAPS&ADAS, part of PReVENT Integrated Project, dedicated to the development, test and validation of a standardized interface (ADAS Interface) between ADAS applications and ADAS map data sources for accessing map data regarding vehicle position.</div>

This paper discusses about the driver state analysis for Advanced Driver Assistance System (ADAS) application in automotive and check whether the driver is drowsy or alert. Driver state analysis is one of the important tasks in today's automotive. In this paper, EEG signals are used for driver state analysis. The sleep data set for analysis is obtained from Physionet. The study of characteristics of EEG signals and its different frequency rhythms like gamma, beta, alpha, theta and delta. The drowsy state indication is observed in alpha and theta frequency rhythms. The data is pre-processed to remove artifacts and features representing drowsiness are extracted. The feature reduction techniques are used to reduce the humongous features whose computation time is more during classification. ADAS application should produce quick response for the analysis of EEG signal, hence the algorithm used to classify the driver state (drowsy/alert) should have less computational time. The comparison of computational time and accuracy of different classification algorithms like SVM and logistic regression is done and the best algorithm with less computational time and more accuracy is selected. The proposed method is used to analyse the driver state and further to analyze different sleep stages for clinical purposes.

Knowledge of the tire-road friction condition is an important key for driver safety and vehicle stability systems during ice and snow road. In particular, friction information can be used to enhance the performance of Advanced Driver-Assistance Systems (ADAS) applications providing real-time forces condition. The paper deals with a method for real-time identification of tyre/road friction condition using both Pacejka model and steady state form of distributed LuGre to obtain the friction based on recursive nonlinear optimization of the curve fitting errors. Finally, the effectiveness of the method is confirmed by real-time simulations in ice and snow conditions.

The advanced driver assistance system (ADAS) for adaptive cruise control and collision avoidance is strongly dependent upon the robust image recognition technology such as lane detection, vehicle/pedestrian detection, and traffic sign recognition. However, the conventional ADAS cannot realize more advanced collision evasion in real environments due to the absence of intelligent vehicle/pedestrian behavior analysis. Moreover, accurate distance estimation is essential in ADAS applications and semiglobal matching (SGM) is most widely adopted for high accuracy, but its system-on-chip (SoC) implementation is difficult due to the massive external memory bandwidth. In this paper, an ADAS SoC with behavior analysis with Artificial Intelligence functions and hardware implementation of SGM is proposed. The proposed SoC has dual-mode operations of highperformance operation for intelligent ADAS with real-time SGM in D-Mode (d-mode) and ultralow-power operation for black box system in parking-mode. It features: 1) task-level pipelined SGM processor to reduce external memory bandwidth by 85.8%; 2) region-of-interest generation processor to reduce 86.2% of computation; 3) mixed-mode intention prediction engine for dualmode intelligence; and 4) dynamic voltage and frequency scaling control to save 36.2% of power in d-mode. The proposed ADAS processor achieves 862 GOPS/W energy efficiency and 31.4GOPS/ mm(2) area efficiency, which are 1.53x and 1.75x improvements than the state of the art, with 30 frames/s throughput under 720p stereo inputs.

The ongoing development of Advanced Driver Assistance Systems (ADAS) requires new prototyping concepts. In this paper the concept vehicle Carai is presented as a generic vehicle with a variety of sensors, computing units, and different HMI components in order to allow the fast implementation and evaluation of different ADAS applications. In addition to the description of the technical components, a software framework is presented which enables fast software prototyping by providing basic data acquisition and processing modules including sophisticated data fusion algorithms. Finally, the usage of the Carai is demonstrated on the example of different ADAS applications.

Desirability of advanced driver assistance from road safety perspective: the case of ISA

The Modularisation Design Approach Applied to the ADAS Domain: The DESERVE Project Experience

ADAS (Advanced Driver Assistance System) applications are computational systems which help drivers in decision making on day-to-day traffic situations. We propose an ADAS application using deep-learning techniques applied in computer vision with the objective to lane segmentation and object detection of common subjects in traffic environment. All the fore mentioned detections are applied to alert a driver about possible collisions with cars, or nearby people. Furthermore, the lane detection has the objective of infer if the driver is deviating from the correct track path. We also propose that the application is deployed and usable in embedded platforms such as NVIDIA’s Jetson family products, to measure applicability we use FPS as a metric both on Jetson Nano and Jetson TX2.

ABCDWaveNet: Advancing Robust Road Ponding Detection in Fog Through Dynamic Frequency-Spatial Synergy

Modern Advanced Driver-Assistance Systems (ADAS) combine critical real-time and non-critical best-effort tasks and messages onto an integrated multi-core multi-SoC hardware platform. The real-time safety-critical software tasks have complex interdependencies in the form of end-to-end latency chains featuring, e.g., sensing, processing/sensor fusion, and actuating. The underlying real-time operating systems running on top of the multi-core platform use static cyclic scheduling for the software tasks, while the communication backbone is either realized through PCIe or Time-Sensitive Networking (TSN). In this paper, we address the problem of configuring ADAS platforms for automotive applications, which means deciding the mapping of tasks to processing cores and the scheduling of tasks and messages. Time-critical messages are transmitted in a scheduled manner via the timed-gate mechanism described in IEEE 802.1Qbv according to the pre-computed Gate Control List (GCL) schedule. We study the computation of the assignment of tasks to the available platform CPUs/cores, the static schedule tables for the real-time tasks, as well as the GCLs, such that task and message deadlines, as well as end-to-end task chain latencies, are satisfied. This is an intractable combinatorial optimization problem. As the ADAS platforms and applications become increasingly complex, such problems cannot be optimally solved and require problem-specific heuristics or metaheuristics to determine good quality feasible solutions in a reasonable time. We propose two metaheuristic solutions, a Genetic Algorithm (GA) and one based on Simulated Annealing (SA), both creating static schedule tables for tasks by simulating Earliest Deadline First (EDF) dispatching with different task deadlines and offsets. Furthermore, we use a List Scheduling-based heuristic to create the GCLs in platforms featuring a TSN backbone. We evaluate the proposed solution with real-world and synthetic test cases scaled to fit the future requirements of ADAS systems. The results show that our heuristic strategy can find correct solutions that meet the complex timing and dependency constraints at a higher rate than the related work approaches, i.e., the jitter constraints are satisfied in over 6 times more cases, and the task chain constraints are satisfied in 41% more cases on average. Our method scales well with the growing trend of ADAS platforms.

Advanced driver assistance systems (ADAS) are designed to increase driver's situational awareness and road safety by providing essential information, warning and automatic intervention to reduce the possibility/severity of an accident. Of the various types of ADAS modalities available, camera based ADAS are being widely adopted for their usefulness in varied applications, overall reliability and adaptability to new requirements. But camera based ADAS also represents a complex, high-performance, and low-power compute problem, requiring specialized solutions. This paper introduces a high performance front camera ADAS based on a small area, low power System-on-Chip (SoC) solution from Texas Instruments called Texas Instruments Driver Assist 3x (TDA3x). The paper illustrates compute capabilities of the device in implementation of a typical front camera ADAS. The paper also introduces key programming concepts related to heterogeneous programmable compute cores in the SoC and the software framework to use those cores in order to develop the front camera solutions. These aspects will be of interest not only to the ADAS developers but for computer vision and compute intensive embedded system development.

Event-based vision sensors have a higher temporal resolution, a wider dynamic range, and a lower latency than conventional frame-based cameras. For these reasons, event-based sensors are being considered for advanced driver assistance systems applications. If these sensors are to be used for automotive sensing and perception, their performance under adverse conditions, such as rain and fog, must be characterized to ensure reliable performance. This study presents a suite of tests using an event-based sensor under controlled conditions across a range of rainfall rates, ambient light levels, fog visibility levels and distances from the targets. To evaluate the performance of these sensors, the average event rate (number of events per second) was compared with rainfall rates and visibility. The results indicated that the diameter of the raindrops had a larger effect on the number of events than the rainfall rate. Furthermore, the investigation revealed that, by carefully configuring the camera settings, it is possible to mitigate the effects of rain on the sensor output.

Advanced driver assistance systems applications increasingly use cameras and image processing algorithms. To embed and achieve real-time execution of these algorithms, semiconductor companies propose heterogeneous systems-on-chip (SoCs). Embedding algorithms on this type of hardware is not trivial: One needs to determine how to partition the computational load on the different processing units. In addition, it is not easy to predict whether a given algorithm can be executed on a given heterogeneous SoC while meeting real-time constraints. We propose a novel global methodology to assist with embedding image processing algorithms on heterogeneous SoC while meeting real-time constraints (using a soft real-time analysis). Our approach proposes several heuristics predicting delays and execution times and is based on a set of multi-level test vectors which extract key features of heterogeneous architectures.

Estimating the map-matched position of a vehicle on a digital map is a key technology for modern navigation and advanced driver assistance systems (ADAS). Inaccurate sensor measurements and a simplified road network representation cause uncertainties in the map-matched position. This paper describes a particle filter method for finding a robust and stable solution for the map-matching problem at the lane-level in ambiguous situations. The proposed approach fuses low-cost sensor data including camera detections of the lane markings with commercial map data. A new spatio-temporal filtering algorithm is introduced for estimating the hypotheses for the map-matched positions together with a confidence measure from the set of weighted particles. The results of tests at road bifurcations indicate that this method produces stable decisions for the correct road segment. It was found that the integration of lane based features improves the performance of the map-matcher at the road level.

Image recognition technology plays an important role in advanced driver assistance systems (ADAS). The objective of this study is to explore the feasibility of using heterogeneous image fusion to improve the object detection performance of the ADAS. Among the many possible combinations of image types, the fusion of infrared (IR) and visible (VIS) images has great potential because of their complementary characteristics. Most studies on image fusion assume that the images involved align themselves perfectly, which is unrealistic. We address this alignment issue in this study, review various methods of image alignment and fusion, and propose an image-fusion approach that combines alignment and fusion methods for the ADAS application. Finally, we used deep learning networks to detect pedestrian and vehicle objects before and after the image fusion. The experimental results show that the fusion of IR and VIS images can improve the object detection performance of deep-learning networks. Compared with previous studies on fusion, the proposed approach ranks top if the detection accuracy improvement and execution speed are considered as a whole. This study also found that, to use image fusion to improve the object detection accuracy of deep learning networks, it is better to use fused images directly instead of unfused VIS images as the training samples.