1 简介
目标跟踪技术在智能交通、安全监控、人机交互和运动分析等领域有着广泛的应用。近些年,目标跟踪技术取得了飞速的发展,涌现出许多优秀的目标跟踪算法,解决了很多棘手的目标跟踪问题。但是,目标跟踪技术仍然面临着很多的挑战,由于现实环境较为复杂,目前的跟踪算法在实时性、精确性等方面还不能满足实际应用。本文对KCF目标跟踪算法进行优化,KCF跟踪算法利用循环矩阵进行密集采样提取图像的HOG特征,使用正则化最小二乘分类器进行训练提高了运行速度。KCF跟踪算法的优势为目标跟踪速度快,在Benmark视频序列集OTB50的平均速度为172fps,平均精度为73.2%。
2 部分代码
function [img_files, pos, target_sz, ground_truth, video_path] = load_video_info(base_path, video)%LOAD_VIDEO_INFO% Loads all the relevant information for the video in the given path:% the list of image files (cell array of strings), initial position% (1x2), target size (1x2), the ground truth information for precision% calculations (Nx2, for N frames), and the path where the images are% located. The ordering of coordinates and sizes is always [y, x].%在给定路径中加载视频的所有相关信息:图像文件列表(字符串单元数组)、初始位置(1x2)、%目标大小(1x2)、用于精确计算的ground truth信息(N帧的Nx2)以及图像所在的路径。%坐标和大小的顺序总是[y, x]。%% Joao F. Henriques, 2014% http://www.isr.uc.pt/~henriques/ %see if there's a suffix, specifying one of multiple targets, for %example the dot and number in 'Jogging.1' or 'Jogging.2'. %{ if numel(video) >= 2 && video(end-1) == '.' && ~isnan(str2double(video(end))), suffix = video(end-1:end); %remember the suffix video = video(1:end-2); %remove it from the video name else suffix = ''; end %full path to the video's files if base_path(end) ~= '/' && base_path(end) ~= '\', base_path(end+1) = '/'; end %} %video_path = [base_path video '/']; %video_path = [base_path video];% video_path = choose_video(base_path);%大概因为这句,所以我需要选择两次视频 video_path = video; %try to load ground truth from text file (Benchmark'sformat) %尝试从文本文件(基准测试的格式)加载ground truth %{ filename = [video_path 'Basketball_gt' suffix '.txt']; f = fopen(filename); assert(f ~= -1, ['No initial position or ground truth to load ("' filename '").']) %the format is [x, y, width, height] try ground_truth = textscan(f, '%f,%f,%f,%f', 'ReturnOnError',false); catch %#ok, try different format (no commas) frewind(f); ground_truth = textscan(f, '%f %f %f %f'); end %} text_files = dir([video_path '*_gt.txt']); assert(~isempty(text_files), 'No initial position and ground truth (*_gt.txt) to load.') f = fopen([video_path text_files(1).name]); ground_truth = textscan(f, '%f,%f,%f,%f');%已经将car4数据进行修改 ground_truth = cat(2, ground_truth{:}); fclose(f); %set initial position and size target_sz = [ground_truth(1,4), ground_truth(1,3)]; pos = [ground_truth(1,2), ground_truth(1,1)] + floor(target_sz/2); if size(ground_truth,1) == 1, %we have ground truth for the first frame only (initial position) ground_truth = []; else %store positions instead of boxes ground_truth = ground_truth(:,[2,1]) + ground_truth(:,[4,3]) / 2; end %from now on, work in the subfolder where all the images are video_path = [video_path 'imgs/']; %f or these sequences, we must limit ourselves to a range of frames. %for all others, we just load all png/jpg files in the folder. frames = {'David', 300, 770; 'Football1', 1, 74; 'Freeman3', 1, 460; 'Freeman4', 1, 283}; idx = find(strcmpi(video, frames(:,1))); if isempty(idx), %general case, just list all images img_files = dir([video_path '*.png']); if isempty(img_files), img_files = dir([video_path '*.jpg']); assert(~isempty(img_files), 'No image files to load.') end img_files = sort({img_files.name}); else %list specified frames. try png first, then jpg. if exist(sprintf('%s%04i.png', video_path, frames{idx,2}), 'file'), img_files = num2str((frames{idx,2} : frames{idx,3})', '%04i.png'); elseif exist(sprintf('%s%04i.jpg', video_path, frames{idx,2}), 'file'), img_files = num2str((frames{idx,2} : frames{idx,3})', '%04i.jpg'); else error('No image files to load.') end img_files = cellstr(img_files); end end
3 仿真结果
4 参考文献
[1] J. F. Henriques, R. Caseiro, P. Martins, J. Batista, "High-Speed Tracking with
Kernelized Correlation Filters", TPAMI 2014 (to be published).
[2] J. F. Henriques, R. Caseiro, P. Martins, J. Batista, "Exploiting the Circulant
Structure of Tracking-by-detection with Kernels", ECCV 2012.
[3] Y. Wu, J. Lim, M.-H. Yang, "Online Object Tracking: A Benchmark", CVPR 2013.
Website: http://visual-tracking.net/
[4] P. Dollar, "Piotr's Image and Video Matlab Toolbox (PMT)".
Website: http://vision.ucsd.edu/~pdollar/toolbox/doc/index.html
[5] P. Dollar, S. Belongie, P. Perona, "The Fastest Pedestrian Detector in the
West", BMVC 2010.
博主简介:擅长智能优化算法、神经网络预测、信号处理、元胞自动机、图像处理、路径规划、无人机等多种领域的Matlab仿真,相关matlab代码问题可私信交流。
部分理论引用网络文献,若有侵权联系博主删除。
适适