基于贝叶斯模型的相机间人群目标识别

准确获取相互遮挡粘连目标的位置特征,是在视野有重叠区域条件下进行相机间目标识别的关键。提出首先构造人体模型,利用贝叶斯模型将粘连目标的分割问题转换为求解最大后验概率问题,然后依据获得的目标轴线特征,在不同的相机间按照最小距离原则进行相同目标的匹配识别。结果表明,利用人体模型进行人群分割的抗干扰能力强,目标识别的准确率较高。     

Multi-scale-based joint super-resolution and inverse tone-mapping with data synthesis for UHD HDR video

The performance of current joint super-resolution (SR) and inverse tone-mapping (ITM) frameworks is limited since they only account for information in small local receptive fields. Moreover, the SDR images in the existing dataset for joint SR-ITM are oversaturated compared to the HDR ground truths. The models trained on this dataset produce HDR images with color shift. This paper proposes a multi-scale-based joint SR-ITM model to reconstruct HR HDR videos. Image features are downsampled to different resolutions to increase the local receptive fields. Thus the proposed model can react to more complex patterns of input images. And we design a novel multi-path residual dense block (MRDB) as the model’s fundamental component to extract features. The proposed MRDBs can improve performance by combining dense feature learning and novel multi-path residual learning. Experiments show that the proposed model outperforms the state-of-the-art methods in terms of quantitative and qualitative results. Furthermore, we propose a data synthesis pipeline to generate perceptually identical SDR images from their HDR counterparts. These SDR-HDR pairs are used to create a new dataset. Experiments demonstrate that models trained with our new dataset prevent color shift and preserve creative intent.     

融合双注意力机制的人群计数算法

针对背景复杂、遮挡、人群分布不均等人群计数常见问题,提出了一种结合联合损失的空间-通道双注意力机制卷积神经网络模型(joint loss-based space-channel dual attention network, JL-SCDANet).该网络前端进行图像粗粒度特征提取,中间加入空间注意力机制以及通道注意力机制突出图像重点区域,后端使用可加大感受野且不丢失图像分辨率的空洞卷积提取深层二维特征.此外,该模型结合联合损失函数进行训练,以增强模型的鲁棒性.为了验证模型的改进效果,在3个公共数据集(ShanghaiTech Part B、mall和UCF＿CC＿50)上分别进行了对比实验,在ShanghaiTech Part B数据集中平均绝对误差(MAE)和均方误差(MSE)分别达到了8.13和13.13;在mall数据集中MAE、MSE达到了1.78和2.28;在UCF＿CC＿50数据集中MAE、MSE分别达到了182.12和210.24,实验结果证明了该网络在提高人数统计准确率上的有效性.     

Motion detection in moving camera videos using background modeling and FlowNet

Real-time moving object detection is challenging for moving cameras due to the moving background. Many studies use homography matrix to compensate for global motion by warping the background model to the current frame. Then, the pixel difference between the current frame and the background model is used for background subtraction. Moving pixels are extracted by applying adaptive threshold and some post-processing techniques. On the other hand, deep learning-based dense optical flow can be efficient enough to extract the moving pixels, but it increases computational cost. This study proposes a method to enhance a classical background modeling method with deep learning-based dense optical flow. The main contribution of this paper is to propose a fusing algorithm for dense optical flow and background modeling approach. The background modeling methods are error-prone, especially with continuous camera movement, while the optical flow method alone may not always be efficient. Our hybrid method fuses both techniques to improve the detection accuracy. We propose a software architecture to run background modeling and dense optical flow methods in parallel processes. The proposed implementation approach significantly increases the method’s working speed, while the proposed fusion and combining strategy improve detection results. The experimental results show that the proposed method can run at high speed and has satisfying performance against the methods in the literature.     

一种抗背景干扰的多尺度人群计数算法

人群计数技术以估计人群图片或视频中的人数为目标,可以有效预防人群踩踏事故的发生,广泛应用于安防预警、城市规划及大型集会管理等领域。然而,由于人群尺度变化、背景干扰、人群分布不均、遮挡和透视效应等因素的影响,单幅图片的人群计数仍是一项非常具有挑战性的任务。针对人群计数中多尺度变化和背景干扰问题,提出一种抗背景干扰的多尺度人群计数算法。以VGG16网络结构为基础,引入特征金字塔构建多尺度特征融合骨干网络解决人群多尺度变化问题,设计Double-Head-CC结构对融合后的特征图进行前景背景分割和密度图预测以抑制背景干扰。基于密度图的局部相关性和多任务学习,定义多重损失函数和多任务联合损失函数进行网络优化。在ShanghaiTech、UCF-QNRF和JHU-CROWD++数据集上进行训练和评测,实验结果表明,该算法能够很好地预测人群密度分布和人群数量,具有较高的准确性,且鲁棒性强、泛化性能良好。     

基于运动矢量交点密集度的人群恐慌行为检测

为了更准确有效的识别人群恐慌行为,本文提出了一种利用视频中人群运动矢量的交点密集度来判断人群恐慌异常的新算法.该算法以LK光流法为基础来提取运动人群的运动矢量信息,接着通过获得的信息求取运动矢量间的两两交叉点,然后运用分块法求得区域交叉点密集度,并以此来识别人群异常.对多个视频进行测试,测试结果表明:该算法能够以较高正确率识别视频中人群的恐慌行为.     

基于粒子视频的高密度人群主流运动检测

采用粒子视频流获得视频序列中的特征点运动轨迹,并对获得的运动轨迹进行提取,然后利用最长共同子序列LCS(Longest Common Subsequence)聚类轨迹,得到运动的主流方向。该算法可以有效检测实际场景中的主流运动方向。     

Solving knapsack problems on GPU

A parallel implementation via CUDA of the dynamic programming method for the knapsack problem on NVIDIA GPU is presented. A GTX 260 card with 192 cores (1.4 GHz) is used for computational tests and processing times obtained with the parallel code are compared to the sequential one on a CPU with an Intel Xeon 3.0 GHz. The results show a speedup factor of 26 for large size problems. Furthermore, in order to limit the communication between the CPU and the GPU, a compression technique is presented which decreases significantly the memory occupancy.     

Wandering crowd simulation based on space syntax theory

Space syntax has proven there appears to be a fundamental process that informs human and social usage of an environment,and the effects of spatial configuration on movement patterns are consistent with a model of individual decision behavior.Introducing space syntax to crowd simulation will enable space structure guide the random movement of the crowd with no specific targets.This paper proposes a simulation method of the wandering crowd,which calculates the crowd distribution corresponding to the space through space syntax and uses a hybrid path planning algorithm to dynamically navigate the crowd to conform to the distribution.Experiments show the presented method can obtain reasonable and vision-realistic simulation results.