Vehicle detection is essential for driverless systems. However, the current single sensor detection mode is no longer sufficient in complex and changing traffic environments. Therefore, this paper combines camera and light detection and ranging (LiDAR) to build a vehicle-detection framework that has the characteristics of multi adaptability, high real-time capacity, and robustness. First, a multi-adaptive high-precision depth-completion method was proposed to convert the 2D LiDAR sparse depth map into a dense depth map, so that the two sensors are aligned with each other at the data level. Then, the You Only Look Once Version 3 (YOLOv3) real-time object detection model was used to detect the color image and the dense depth map. Finally, a decision-level fusion method based on bounding box fusion and improved Dempster–Shafer (D–S) evidence theory was proposed to merge the two results of the previous step and obtain the final vehicle position and distance information, which not only improves the detection accuracy but also improves the robustness of the whole framework. We evaluated our method using the KITTI dataset and the Waymo Open Dataset, and the results show the effectiveness of the proposed depth completion method and multi-sensor fusion strategy.

No abstract

In view of the strict requirements of the current high-precision measurement system for stable output power of the semiconductor LD (Laser Diode), a semiconductor LD stable power drive and multi-closed-loop control system are proposed after analyzing the semiconductor laser’s P–I (Power–Current) characteristics and temperature characteristics. The system uses a microcontroller as the core control unit and realizes the stable power output control of the semiconductor laser by controlling the current, power and temperature parameters. In this system, first, the control structure model of the controlled object has been designed. Second, a controllable closed-loop constant current feedback drive circuit has been designed and a high-precision controllable constant current drive circuit of the semiconductor laser has been obtained. Furthermore, the control circuit has been designed based on the neural PI (Proportional-Integral) control model and realizes the short-term stable power output of the semiconductor LD. Finally, a closed-loop temperature control system is designed to ensure that the operating temperature of the semiconductor laser is relatively stable and a long-term stable power output is obtained. By designing the hardware and software of the control system and conducting long-term experiments in the laboratory, we found that the system can guarantee the output power within 1 W of PD (Proportional-Differential) LD, and its long-term power stability can reach 1%. This system has a certain reference significance in using semiconductor lasers for high-quality detection when there are stringent requirements for power.

No abstract

In any given collaboration, information needs to flow from one participant to another. While participants may be interested in sharing information with one another, it is often necessary for them to establish the impact of sharing certain kinds of information. This is because certain information could have detrimental effects when it ends up in wrong hands. For this reason, any would-be participant in a collaboration may need to establish the guarantees that the collaboration provides, in terms of protecting sensitive information, before joining the collaboration as well as evaluating the impact of sharing a given piece of information with a given set of entities. The concept of a trust domains aims at managing trust-related issues in information sharing. It is essential for enabling efficient collaborations. Therefore, this research attempts to develop a taxonomy for trust domains with measurable trust characteristics, which provides security-enhanced, distributed containers for the next generation of composite electronic services for supporting collaboration and data exchange within and across multiple organisations. Then the developed taxonomy is applied to a possible scenario, in which the concept of trust domains could be useful.