Communication Network Architectures for Driver Assistance Systems

Abstract

Autonomous Driver Assistance Systems (ADAS) are of increasing importance to warn vehicle drivers of potential dangerous situations. In this paper, we propose one system to warn drivers of the presence of pedestrians crossing the road. The considered ADAS adopts a CNN-based pedestrian detector (PD) using the images captured from a local camera and to generate alarms. Warning messages are then forwarded to vehicle drivers approaching the crossroad by means of a communication infrastructure using public radio networks and/or local area wireless technologies. Three possible communication architectures for ADAS are presented and analyzed in this paper. One format for the alert message is also presented. Performance of the PDs are analyzed in terms of accuracy, precision, and recall. Results show that the accuracy of the PD varies from 70% to 100% depending on the resolution of the videos. The effectiveness of each of the considered communication solutions for ADAS is evaluated in terms of the time required to forward the alert message to drivers. The overall latency including the PD processing and the alert communication time is then used to define the vehicle braking curve, which is required to avoid collision with the pedestrian at the crossroad.

MuSLi: A multi sensor LiDAR detection for C-V2X networks

“…In order to assess the latencies for each scenario and in each environment, in Table 2 we report the range of values, elaborated from [22] and [23]. In our analysis, in addition to V2I and V2V, for V2N we considered (i ) two sub-carrier spacing (SCS) values of 15 kHz and 60 kHz, with a slot duration of 1 ms and 0.125 ms, respectively, and (ii ) a mini-slot case with 7 OFDM symbols.…”

Road User Position and Speed Estimation via Deep Learning from Calibrated Fisheye Videos

“…Finally, we partly address edge computing and we do not deal with the transmission delay added by the network communication. The latter is well dealt with by [11].…”

“…This kind of bird's-eye view also minimizes the risk of object oc sions compared to a traditional perspective view. The work presented in this pape quite similar but complementary to that of [11], since the latter deals only with the de tion of pedestrians, whereas we deal with all road users. The main contributions of our work are:…”