Search Results

The around view monitor (AVM) system for vehicles usually suffers from the distortion of surrounding objects caused by incomplete rectification and stitching, which seriously affects the driver's judgment of the surrounding environment during the reversing process. In response to solve this problem, an augmented around view monitor (AAVM) system fusing image and depth information is proposed, which highlights the point clouds of persons or vehicles at the rear of the vehicle. First, an around view image is generated from four fisheye cameras. Then, the calibration of multi TOF cameras is conducted to improve their accuracy of depth estimation and obtain extrinsic camera positions. Next, the 2D-driven object point cloud detection method is proposed to localize and segment object point clouds like vehicles or persons.

The driver's face detection and tracking method important for Advanced Driver Assistance Systems (ADAS) and autonomous driving in various situations. The deep SORT algorithm has integrated appearance information, the motion model and the intersection-over-union (IOU) distance methods, and has been applied to face tracking, but it depends on detection information in every frame. Once the detection information lacks, the deep SORT algorithm will wait until the target detects bounding boxes appear again, even if the target didn’t disappear or shield. Hence, we propose to use a new tracker that not completely depend on the detection algorithm to cascade with the deep SORT algorithm to realize stable driver's face tracking. At first, the driver's face detection and tracking will be accomplished by the MTCNN-deep-SORT algorithm.

A 32-week pregnant 5th percentile female occupant model was developed. The uterus with fetus, amniotic fluid, placenta, fat, and ligaments, etc. was modeled by finite element methods, and it was integrated into MADYMO facet 5th percentile female occupant model. The model was validated via abdominal response corridors under belt loading and bar loading. It was used to study the strain of the uterine wall where the placental is contacted during car crash accidents, for the placental abruption is one of the major risks to the fetus. The simulation results show that the traditional 3-pt belt may not provide good protection for the fetus due to large strain can be found during car crash. So, two kinds of new belts were presented. They use different kinds of sheets to enwrap the protuberant abdomen of the pregnant female occupant in order to decrease the movement of the uterus relatively to the body. Thus, the strain of the uterine wall can be decreased significantly.

Statistic analysis on commercial vehicle crash accidents in China were done by using the annual traffic accident reports from Ministry of Public Security. The Chinese crash safety rules on commercial vehicle were introduced. The main reasons which cause severe injury to the passenger in the cab in frontal crash accidents were studied. HYPERMESH software was used to do the finite element modelling of the frontal structure and cab of a production truck. The swing hammer impact simulation was conducted by using LS-DYNA software and the results were compared with the test results to validate the model. A new supporting structure for the cab to improve the safety of the passenger in cab was proposed. Meanwhile, an extendable and retractable longitudinal beam energy absorbing structure was also studied by using the finite element model. The simulation results show that these structures can obviously improve the frontal crash safety of the commercial vehicle.

The research question investigated in this study is what are the key attributes of foot and ankle injury in the between-rail frontal crash? For the foot and ankle, what was the type of interior surface contacted and the type of resulting trauma? The method was to study with in-depth case reviews of NASS-CDS cases where a driver suffered an AIS=2 foot or ankle injury in between-rail crashes. Cases were limited to belted occupants in vehicles equipped with air bags. The reviews concentrated on coded and non-coded data, identifying especially those factors contributing to the injuries of the driver's foot/ankle. This study examines real-world crash data between the years 1997-2009 with a focus on frontal crashes involving 1997 and later model year vehicles. The raw data count for between-rail crashes was 732, corresponding to 227,305 weighted, tow-away crashes.

In order to provide an improved countermeasure for occupant protection, a new type of active reversible preload seatbelt (ARPS) is presented in this paper. The ARPS is capable of protecting occupants by reducing injuries during frontal collisions. ARPS retracts seatbelt webbing by activating an electric motor attached to the seatbelt retractor. FCW (Forward Collision Warning) and LDW (Lane Departure Warning) provide signals as a trigger to activate the electric motor to retract the seatbelt webbing, thus making the occupant restraint system work more effectively in a crash. It also helps reduce occupant’s forward movement during impact process via braking. Four important factors such as preload force, preload velocity and the length and timing of webbing retraction play influential roles in performance of the ARPS. This paper focuses on studying preload performance of ARPS under various test conditions to investigate effects of the aforementioned factors.

The combination of passive and active vehicle safety technologies can effectively improve vehicle safety. Most of them predict vehicle crashes using radar or video, but they can't be applied extensively currently due to the high cost. Another collision forecasting method is more economic which is based on the driver behavior and vehicle status, such as the acceleration, angular velocity of the brake pedal and so on. However, the acceleration and angular velocity of the brake pedal will change with the driver and the vehicle type. In order to study the effect of different drivers and vehicle types on the braking acceleration and angular velocity of the brake pedal, six volunteers were asked to drive five vehicles for simulating the working conditions of emergency braking, normal braking, inching braking and passing barricades under different velocities. All the tests were conducted on asphalt road, and comprehensive experimental design was used to arrange tests.

Panoramic images can provide critical information for Advanced Driving Assistance Systems (ADAS), such as parking spaces and surrounding vehicles. However, the vehicle in the bird's-eye view image is severely distorted and incomplete, and the visual information becomes very blurred in some illumination insufficient environments. If the driver cannot see the surrounding environment information, the risk of collision will increase, especially during parking. To better percept the local environment with the help of panoramic images, we use panoramic image segmentation results to construct a virtual surround view monitoring system to provide drivers with clearer perception information. Firstly, a lightweight segmentation network is redesigned based on SegNet, which will improve the accuracy of the segmentation without increasing the model’s inference time. Secondly, we build an augment visualization around view monitor (AV-AVM) system with regards to the segmentation results.