To solve traffic congestion problems, a new road condition judgment model was proposed. Firstly, the model was based on YOLOv3 target detection algorithm. Then, according to the eigenvalue matrix corresponding to the picture, the difference between adjacent frames was made by the eigenvalue matrix, and the difference value was compared with preset value to determine whether the current road was in a congested state or a normal traffic state. Secondly, the current calculated road state was compared with previous two calculated road states. Finally, the state statistics method in the model was used to calculate the duration of a state (congestion or patency) of road. The proposed model could analyze the states of three lanes of a road at the same time. Through experiments, the average accuracy of model to judge the state of single lane could reach 80% or more, and it was applicable to both day and night roads.

Some problems of the current load balancing algorithms for distributed systems include:1) The role of each node in the system is fixed, and the system has no adaptability. 2) The load balancing algorithm is not universal. 3) The migration task is too large, and the load balance cycle is too long. To solve these problems, a hybrid load balancing algorithm was proposed. Firstly, a distributed receiving system model was designed, by which the system tasks were divided into three parts:receiving level, handling level and storing level. In receiving level, a home-made transmission protocol was used to improve the reception capability of the system. And then, in the load balancing algorithm, random load migration strategy was used. According to the status of the nodes, the tasks of load were randomly migrated. The problems of long load balance cycle and load moving back were solved by this strategy. Finally, the distributed control node selecting strategy was adopted to make the nodes adaptable. The experimental results show that the average delay in each layer of the system is in milliseconds, and the system load balancing takes less than 3 minutes, which proves that the load balancing mechanism has short load balance cycle and fast response, and can improve the reception capability of the distributed system.

Focusing on low counting accuracy caused by serious occlusions and abrupt illumination variations, a new real-time statistical method based on Gaussian Mixture Model (GMM) and Scale-Invariant Feature Transform (SIFT) features for video crowd counting was proposed. Firstly, the moving crowd were detected by using GMM-based motion segment method, and then the Gray Level Co Occurrence Matrix (GLCM) and morphological operations were applied to remove small moving objects of background and the dense noise in non-crowd foreground. Considering the high time-complexity of GMM algorithm, a novel parallel model with higher efficiency was proposed. Secondly, the SIFT feature points were acted as the basis of crowd statistics, and the execution time was reduced by using feature exaction based on binary image. Finally, a novel statistical analysis method based on crowd features and crowd number was proposed. The data sets with different level of crowd number were chosen to train and get the average feature number of a single person, and the pedestrians with different densities were counted in the experiment. The algorithm was accelerated by using multi-stream processors on Graphics Processing Unit (GPU) and the analysis about efficiently scheduling the tasks on Compute Unified Device Architecture (CUDA) streams in practical applications was conducted. The experimental results indicate that the speed is increased by 31.5% compared with single stream, by 71.8% compared with CPU.

To improve the safety of vehicles while driving, a computer vision-based inter-vehicle distance estimation and warning method was proposed in this paper. First, shadow detection method was applied to detect shadow of cars ahead, and inter-vehicle distance estimation function was built based on the distance between shadow and vision center of a frame. Then, estimation equations for non-threatened background optical flow was built, and by judging optical flow with the estimation equations, the abnormal objects could be separated from others, thus the overtaking event could be recognized. Based on the inter-vehicle distance and detection of overtaking event, the driver could be timely warned of the potential safety hazard. The experimental results prove that the proposed method can estimate inter-vehicle distance and detect overtaking event accurately. Finally, NVIDIA GeForce GTX680 GPU (Graphic Processing Unit) was used to accelerate the algorithm on Compute Unified Device Architecture (CUDA) platform and achieve the processing speed of 48.9 ms per frame which basically meets the real-time processing demand.

Since the segmentation performance of existing binary segmentation algorithm for video is excessively low, a binary probability segmentation algorithm in real-time based on Graphics Processing Unit (GPU) was proposed. The algorithm implemented a probabilistic segmentation based on the Quadratic Markov Measure Field (QMMF) model by regularizing the likelihood of each pixel of frame belonging to forground class or background class. In this algorithm, first two kinds of likelihood models, Static Background Likelihood Model (SBLM) and Unstable Background Likelihood Model (UBLM) were proposed. Secondly, the probability of each pixel belonging to background was computed by tonal transforming, cast shadow detecting and camouflage detecting algorithm. Finally, the probability of background which makes the energy function have a minimum value was computed by Gauss-Seidel model iteration and the binary value of each pixel was calculated. Moreover, illumination change, cast shadow and camouflage were included to improve the accuracy of segmentation algorithm. In order to fulfill the real-time requirement, a parallel version of our algorithm was implemented in a NVIDIA GPU. The accuracy and GPU execution time of the segmentation algorithm were analyzed. The experimental results show that the average missing rate and false detection rate of ViBe+ and GMM+ are 3 and 6 times those of QMMF, the average execution time of GPU of ViBe+ and GMM+ is about 1.3 times that of QMMF. Moreover, the average speedup of algorithm was computed and it is about 76.8.

At present, in the field of target recognition, the highest accuracy algorithm is the Deformable Part Model (DPM) for human detection. Aiming at the disadvantage of large amount of calculation, a parallel solution method based on Graphics Processing Unit (GPU) was proposed. In this paper, with the GPU programming model of OpenCL, the details of the whole DPM algorithm were implemented by the parallel methods,and optimization of the memory model and threads allocation was made. Through the comparison of the OpenCV library and the GPU implementation, under the premise of ensuring the detection effect, the execution efficiency of the algorithm was increased by nearly 8 times.

It is difficult for users to find the needed items from a large-scale project resource repository because the project resources in it are disordered, so a parallel fuzzy partition algorithm based on MapReduce was proposed. The algorithm firstly abstracted and standardized characteristic attributes of original project resource. Then a similarity matrix was established based on the standardized characteristic attributes of the project, and it was segmented by using block matrix. MapReduce was used to process the block matrix and merge the results. Finally, the algorithm obtained the partition results according to the threshold. The contrast experiment among the proposed algorithm, K-means algorithm and genetic algorithm shows that the proposed algorithm has higher accuracy and recall, it can achieve better speedup in large-scale data calculation and divide project resources effectively and accurately.

In the Wireless Sensor Network (WSN) routing, if the node does not fully consider the path node residual energy and link status of the route, some nodes will be dead early, hence the lifetime of the network will be shorten seriously. To resolve this problem, a uneven clustering routing algorithm for wireless sensor network was proposed based on ant colony optimization algorithm. Firstly, the method clustered nodes using uneven clustering algorithm which considered the node energy. Then considering the node need to transmit data as source node, the sink node as destination node, ant colony optimization algorithm was used to do multipath searching, and the searching process fully considered the factors such as transmission energy consumption, path minimum residual energy, transmission distance and transmission hops, time delay and bandwidth of selected link. Several optimal paths that met the conditions were given to complete the information transmission between source and the destination nodes at last. The experimental results show that the lifetime of WSN can be effectively prolonged while fully considering the path transmission energy consumption, path minimum residual energy and transmission hops.

To solve the system integration problem caused by heterogeneous sensor networks, this paper proposed a heterogeneous sensor networks integration system ISHSN (Integration System for Heterogeneous Sensor Network). ISHSN consisted of the gateway of the Internet of Things (IoT) and the access Agent. The gateway converted the data to the same format and converted the command to the customized format according the target sensor network. The access Agent dealt with data collection, link merge and command forward, and balance loading of the access Agents with the scheduling algorithm. The experiment proves that the ISHSN has good scalability and availability in sensor networks data collection and sensor network control.