Abstract
The relatively complex task of detecting 3D objects is essential in the realm of autonomous driving. The related algorithmic processes generally produce an output that consists of a series of 3D bounding boxes that are placed around specific objects of interest. The related scientific literature usually suggests that the data that are generated by different sensors or data acquisition devices are combined in order to work around inherent limitations that are determined by the consideration of singular devices. Nevertheless, there are practical issues that cannot be addressed reliably and efficiently through this strategy, such as the limited field-of-view, and the low-point density of acquired data. This paper reports a contribution that analyzes the possibility of efficiently and effectively using 3D object detection in a cooperative fashion. The evaluation of the described approach is performed through the consideration of driving data that is collected through a partnership with several car manufacturers. Considering their real-world relevance, two driving contexts are analyzed: a roundabout, and a T-junction. The evaluation shows that cooperative perception is able to isolate more than 90% of the 3D entities, as compared to approximately 25% in the case when singular sensing devices are used. The experimental setup that generated the data that this paper describes, and the related 3D object detection system, are currently actively used by the respective car manufacturers’ research groups in order to fine tune and improve their autonomous cars’ driving modules.
Highlights
The role of autonomous driving components is to collect relevant data that creates an accurate overview concerning the driving environment
The 3D objects detection process is assessed using four performance metrics. They are intersection relative to union (IRTU), recall, precision, and the communication cost, which is defined by the average volume of data that is transmitted between a data acquisition sensor and the central data processing components relative to each image sample
Considering the fusion schemes that are presented in the introductory part of this paper, the purpose of this experiment is to compare the performance of early fusion (EF) and late fusion (LF) schemes considering the effective detection performance, and the communication cost and computational time
Summary
The role of autonomous driving components is to collect relevant data that creates an accurate overview concerning the driving environment. Considering the aspects presented above, this paper proposes the detection of 3D objects through both schemes, the late and early detection schemes This essentially results in a detection scheme that supports the late and early detection models, which can be used as required at the level of the central data processing components. It includes a review of the most relevant fusion based detection schemes, which have been studied during the initial stages of the research. The central data processing components send the results of this data processing to the autonomous vehicles that drive in the neighbourhood This overall process occurs in a real-time fashion, as is demonstrated by the outcomes of the experimental assessment that is presented in this paper. This research prototype and the developments that are reported in this paper are actively considered by the relevant research teams that work on the development of autonomous driving software routines
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have