The continuous development in the construction of transportation infrastructure has brought enormous pressure to traffic control. Accurate and detailed traffic flow information is valuable for an effective traffic control strategy. This paper proposes a video-based vehicle counting framework using a three-component process of object detection, object tracking, and trajectory processing to obtain the traffic flow information. First, a dataset for vehicle object detection (VDD) and a standard dataset for verifying the vehicle counting results (VCD) were established. The object detection was then completed by deep learning with VDD. Using this detection, a matching algorithm was designed to perform multi-object tracking in combination with a traditional tracking method. Trajectories of the moving objects were obtained using this approach. Finally, a trajectory counting algorithm based on encoding is proposed. The vehicles were counted according to the vehicle categories and their moving route to obtain detailed traffic flow information. The results demonstrated that the overall accuracy of our method for vehicle counting can reach more than 90%. The running rate of the proposed framework is 20.7 frames/s on the VCD. Therefore, the proposed vehicle counting framework is capable of acquiring reliable traffic flow information, which is likely applicable to intelligent traffic control and dynamic signal timing. INDEX TERMS Object detection, object tracking, trajectory processing, vehicle counting.

No abstract

In this paper, a sensor based on polyvinylidene fluoride (PVDF) piezoelectric thin film was designed and fabricated to detect wrist motion signals. A series of dynamic experiments have been carried out, including the contrast experiments of different materials and force-charge signal characterization. The experimental results show that when the excitation signal exceeds 15 Hz, the sensitivity of the sensor is always stable at 3.10 pC/N. The signal acquisition experiment of the wrist motion has been carried out by using this sensor. The experiment results show that, with the advantages of small size, good flexibility, and high sensitivity, this wrist PVDF sensor can be used to detect the wrist motion signals with weak amplitude, low frequency, strong interference, and randomness.

No abstract

Using first-principles calculations, we systematically evaluated a series of single-layer porous graphene membranes with different sized pores passivated by hydrogen atoms for separating short alkane isomers (C = 5–7). We found that graphene membranes with appropriate pore size (e.g., the pore19 model whose pore size is 8.0 × 5.8 Å) could efficiently separate dibranched isomers from their monobranched and linear counterparts. When alkane molecules diffused through a membrane, the porous graphene might exhibit significant distortion. At the same time, the passing molecule would be forced to change its own geometry as well. More importantly, we found that the geometric deformations of both the penetrating molecule and the membrane concertedly lowered the diffusion barrier by similar magnitudes. Therefore, when designing two-dimensional (2D) separation materials, it is necessary to consider the geometric flexibility of both the separation material and the molecules to be separated. Our results theoretically verified the feasibility of utilizing porous graphene and possibly other 2D materials for screening alkane isomers, which could lead to a wide range of energy and environment related applications.