I. Suspected Vehicle Early Warning Technology Based on Checkpoints
(1) Technical Principle
By performing secondary recognition on images and utilizing the features of the vehicles (e.g., vehicle make, body color, and vehicle type) extracted from the public security traffic management integrated application platform, the system identifies the vehicles passing through checkpoints to find the suspicious ones. It is also possible for the system to recognize components such as make and color, create a vehicle trajectory feature database, and keep the recognized structured information in the feature database for trajectory retrieval and analysis.
(2) Technical Advantages
1. Early warning accuracy is significantly enhanced.
2. There is no necessity for a blacklist database: The algorithm is capable of directly comparing the information of the identified vehicle with the vehicle registration information to figure out whether the vehicle is carrying out activities that are illegal or suspicious. It also does not have to find information such as suspicious plates, fake plates, overdue uninspected vehicles, and scrapped vehicles to add them to the blacklist for screening thus giving the opportunity of identifying suspicious information quickly.
3. By means of vehicle features (e.g., make, model) it will be possible to trace the route: the secondary recognition software can recognize vehicle features such as make and save them in the vehicle trajectory feature database, therefore, the corresponding trajectory query function can be quickly accomplished.
4. At the same time, the trajectory query of unlicensed vehicles is possible: It returns vehicle feature information for unlicensed vehicles, and thus, a corresponding vehicle trajectory feature database is also created, so the trajectory query function for unlicensed vehicles can be readily accomplished.
(3) Application Scenarios
Real-time interception and inspection of suspected vehicles: If there are conditions for checkpoints to be able to perform interception (e.g., equipped with law enforcement service stations ahead), on the system's early warning, the police on duty can confirm a valid early warning quickly by using the checkpoint information provided by the system. If the early warning is valid, on-site police can carry out the interception and disposal.
Off-site analysis: The system can analyze and confirm the identification of vehicles that have been reported to the off-site violation system. For instance, the system can confirm and analyze the suspicious vehicle information generated and then enter the violation information into the off-site violation system for issuing punishments.
Based on Unlicensed Vehicle Trajectories Identifying Real License Plate Information of Vehicles: Quite a few vehicles intentionally put something over their license plates and then enter Shanghai while driving at excessive speeds on highways. The application of the designed system shows that to tackle such behaviors, the system can extract fixed nearby checkpoints and identify the trajectories of vehicles with the same features (e.g., make, color, type) as the unlicensed illegal vehicles within a nearby time range. In this way, the real license plate number of the vehicle can be obtained via manual confirmation and analysis.
Narrowing the Investigation Scope by Querying Vehicle Features Based on Trajectories: Vehicle-related cases usually require the investigation of an issue through vehicle trajectory. In the situation where the vehicle license plate is unknown, the investigation is barely feasible. Vehicle feature trajectory query function of this system helps to narrow the investigation scope and facilitates the solving of the case.
II. Intelligent Early Warning Technology for Train Operation
(1) Technical Principle
This technology captures the information about the changes in the railway operation environment in real-time, and after processing them, it gets the train status and environmental status leading to the identification of the operation scenario. The real-time change information mainly includes track status information, weather information, signal status information, and train status information.
It combines the real-time change information of the railway operation environment with the damage characteristics of railway facilities and safe operation rules to get the train status and environmental status. Train status there includes train clusters (trains of the same type, same operation route, and same operation mode), train position, and delay time, while environmental status consists of temporary speed limit information and the current status of protective signals.
The system uses the current vehicle and operation status of the train to find the corresponding operation scenario. They then use the operation scenario identification result along with the pre-constructed scenario probability transition matrix to make a rolling prediction of the train's operation scenario at a future time. They then connect the train's journey with the rolling prediction of the operation scenario and then re-run the evolution and identification of the spliced operation trajectory. This technique can determine the very operation scenario in the real dynamic operational environment and the evolving operating trajectory of the train in the future period with high precision.
III. Intelligent Monitoring and Safety Early Warning System for Ship Lock Floating Mooring Bollards
The intelligent monitoring and safety early warning system for ship lock floating mooring bollards include real-time monitoring and early warning as its two major functions. The system is capable of showing present load-bearing condition and giving out early warning notices.
The system is made up of a strain monitoring unit, a management server, and a display terminal. The monitoring system takes in strain data live, sends it to the server via the 4G network, and the terminal shows the load-bearing, system, and early-warning information.
IV. Driving State Determination and Early Warning System Based on Driver Emotion Recognition
This system mainly includes a driver emotion recognition system and a driver driving state determination and behavior early warning system.
The driver emotion recognition system, in general, is done via a driver feature recognition system. Firstly, the driver feature recognition involves the collection of the driver's physiological features (electrocardiogram (ECG), electrodermal activity (EDA), electromyography (EMG), pulse rate (PR), respiratory rate (RR)). Then, the driver's behavioral features (e.g., facial expressions, arm movements) are real-time monitored by in-vehicle cameras. At last, the real-time vehicle information (e.g., vehicle speed, acceleration, steering wheel angular velocity, pedal force, pedal frequency) is also collected for determining the driver's emotional and behavioral states.
The driver driving state determination and behavior early warning system utilizes physiological features, behavioral features, and vehicle driving information obtained from the driver to real-time determine the driver's driving state through the comprehensive fusion of data. Besides, it not only identifies the driver's driving state (normal, aggressive, dangerous) but also grades the dangerous behaviors (Grade I, II, III, IV). The system alerts the driver when their behavioral state is detected as being aggressive and therefore performing poorly; if it considers driving in a risky manner, a message will pop up reminding drivers that it's time for them to hand over control, and finally, the human-machine co-driving mode will be engaged. It is possible for this technology to pinpoint a driver's emotional state accurately, which in turn enables it to figure out a driver's behaviour in different driving safety scenarios thereby having a very strong connection with the enactment of safe traffic practices as well as the further development of advanced driving assistance system.
V. Blind Spot Detection and Safety Early Warning System for Large Vehicles
The major components of the blind spot detection and safety early warning system for large vehicles are an image acquisition system, a photoelectric detection and sensing system, a high-definition display system, an early warning and braking system, and an intelligent control system. These systems work together through the various communication lines to form an integrated network that supports the stable operation of the entire system.
FAQ – Frequently Asked QuestionsAbout Us
1. When and where will the Expo be held?
From May 13–15, 2026, the Expo will be held at Hall C, Xiamen International Conference and Exhibition Center (XICEC), Xiamen, China.
2. What is the exhibition scale?
It is a 40,000 m² event, with over 350 companies exhibiting, and 30,000 professional visitors attending from around the world.
3. What activities are included?
There will be more than 80 professional forums and events discussing smart mobility, transportation communication, safety, and sustainable development, among other topics.
4. How many countries and regions are involved?
The fair has participants from over 80+ countries and regions, and thus, it is considered as an international summit for smart transportation innovation.
5. Are there opportunities for cooperation?
Yes. The Expo is a ground for rich business collaboration opportunities, technology exchanges, and investment possibilities with 1,000+ global partners.
6. Who can I contact for details?
For additional information, you may contact the Organizing Committee via the "Contact Us" section on the official website.
