KCF目标跟踪算法---读取摄像头、图像序列，对检测目标进行实时跟踪，速度、精度高.rar

/* Tracker based on Kernelized Correlation Filter (KCF) [1] and Circulant Structure with Kernels (CSK) [2]. CSK is implemented by using raw gray level features, since it is a single-channel filter. KCF is implemented by using HOG features (the default), since it extends CSK to multiple channels. [1] J. F. Henriques, R. Caseiro, P. Martins, J. Batista, "High-Speed Tracking with Kernelized Correlation Filters", TPAMI 2015. [2] J. F. Henriques, R. Caseiro, P. Martins, J. Batista, "Exploiting the Circulant Structure of Tracking-by-detection with Kernels", ECCV 2012. Authors: Joao Faro, Christian Bailer, Joao F. Henriques Contacts: joaopfaro@gmail.com, Christian.Bailer@dfki.de, henriques@isr.uc.pt Institute of Systems and Robotics - University of Coimbra / Department Augmented Vision DFKI Constructor parameters, all boolean: hog: use HOG features (default), otherwise use raw pixels fixed_window: fix window size (default), otherwise use ROI size (slower but more accurate) multiscale: use multi-scale tracking (default; cannot be used with fixed_window = true) Default values are set for all properties of the tracker depending on the above choices. Their values can be customized further before calling init(): interp_factor: linear interpolation factor for adaptation sigma: gaussian kernel bandwidth lambda: regularization cell_size: HOG cell size padding: area surrounding the target, relative to its size output_sigma_factor: bandwidth of gaussian target template_size: template size in pixels, 0 to use ROI size scale_step: scale step for multi-scale estimation, 1 to disable it scale_weight: to downweight detection scores of other scales for added stability For speed, the value (template_size/cell_size) should be a power of 2 or a product of small prime numbers. Inputs to init(): image is the initial frame. roi is a cv::Rect with the target positions in the initial frame Inputs to update(): image is the current frame. Outputs of update(): cv::Rect with target positions for the current frame By downloading, copying, installing or using the software you agree to this license. If you do not agree to this license, do not download, install, copy or use the software. License Agreement For Open Source Computer Vision Library (3-clause BSD License) Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met: * Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer. * Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution. * Neither the names of the copyright holders nor the names of the contributors may be used to endorse or promote products derived from this software without specific prior written permission. This software is provided by the copyright holders and contributors "as is" and any express or implied warranties, including, but not limited to, the implied warranties of merchantability and fitness for a particular purpose are disclaimed. In no event shall copyright holders or contributors be liable for any direct, indirect, incidental, special, exemplary, or consequential damages (including, but not limited to, procurement of substitute goods or services; loss of use, data, or profits; or business interruption) however caused and on any theory of liability, whether in contract, strict liability, or tort (including negligence or otherwise) arising in any way out of the use of this software, even if advised of the possibility of such damage. */ #include "stdafx.h" #ifndef _KCFTRACKER_HEADERS #include "kcftracker.hpp" #include "ffttools.hpp" #include "recttools.hpp" #include "fhog.hpp" #include "labdata.hpp" #endif // Constructor KCFTracker::KCFTracker(bool hog, bool fixed_window, bool multiscale, bool lab) { // Parameters equal in all cases lambda = 0.0001; padding = 2.5; //output_sigma_factor = 0.1; output_sigma_factor = 0.125; if (hog) { // HOG // VOT interp_factor = 0.012; sigma = 0.6; // TPAMI //interp_factor = 0.02; //sigma = 0.5; cell_size = 4; _hogfeatures = true; if (lab) { interp_factor = 0.005; sigma = 0.4; //output_sigma_factor = 0.025; output_sigma_factor = 0.1; _labfeatures = true; _labCentroids = cv::Mat(nClusters, 3, CV_32FC1, &data); cell_sizeQ = cell_size*cell_size; } else{ _labfeatures = false; } } else { // RAW interp_factor = 0.075; sigma = 0.2; cell_size = 1; _hogfeatures = false; if (lab) { printf("Lab features are only used with HOG features.\n"); _labfeatures = false; } } if (multiscale) { // multiscale template_size = 96; //template_size = 100; scale_step = 1.05; scale_weight = 0.95; if (!fixed_window) { //printf("Multiscale does not support non-fixed window.\n"); fixed_window = true; } } else if (fixed_window) { // fit correction without multiscale template_size = 96; //template_size = 100; scale_step = 1; } else { template_size = 1; scale_step = 1; } } // Initialize tracker void KCFTracker::init(const cv::Rect &roi, cv::Mat image) { _roi = roi; assert(roi.width >= 0 && roi.height >= 0); _tmpl = getFeatures(image, 1); _prob = createGaussianPeak(size_patch[0], size_patch[1]); _alphaf = cv::Mat(size_patch[0], size_patch[1], CV_32FC2, float(0)); //_num = cv::Mat(size_patch[0], size_patch[1], CV_32FC2, float(0)); //_den = cv::Mat(size_patch[0], size_patch[1], CV_32FC2, float(0)); train(_tmpl, 1.0); // train with initial frame } // Update position based on the new frame cv::Rect KCFTracker::update(cv::Mat image) { if (_roi.x + _roi.width <= 0) _roi.x = -_roi.width + 1; if (_roi.y + _roi.height <= 0) _roi.y = -_roi.height + 1; if (_roi.x >= image.cols - 1) _roi.x = image.cols - 2; if (_roi.y >= image.rows - 1) _roi.y = image.rows - 2; float cx = _roi.x + _roi.width / 2.0f; float cy = _roi.y + _roi.height / 2.0f; float peak_value; cv::Point2f res = detect(_tmpl, getFeatures(image, 0, 1.0f), peak_value); if (scale_step != 1) { // Test at a smaller _scale float new_peak_value; cv::Point2f new_res = detect(_tmpl, getFeatures(image, 0, 1.0f / scale_step), new_peak_value); if (scale_weight * new_peak_value > peak_value) { res = new_res; peak_value = new_peak_value; _scale /= scale_step; _roi.width /= scale_step; _roi.height /= scale_step; } // Test at a bigger _scale new_res = detect(_tmpl, getFeatures(image, 0, scale_step), new_peak_value); if (scale_weight * new_peak_value > peak_value) { res = new_res; peak_value = new_peak_value; _scale *= scale_step; _roi.width *= scale_step; _roi.height *= scale_step; } } // Adjust by cell size and _scale _roi.x = cx - _roi.width / 2.0f + ((float) res.x * cell_size * _scale); _roi.y = cy - _roi.height / 2.0f + ((float) res.y * cell_size * _scale); if (_roi.x >= image.cols - 1) _roi.x = image.cols - 1; if (_roi.y >= image.rows - 1) _roi.y = image.rows - 1; if (_roi.x + _roi.width <= 0) _roi.x = -_roi.width + 2; if (_roi.y + _roi.height <= 0) _roi.y = -_roi.height + 2; assert(_roi.width >= 0 && _roi