#include <pcl/people/person_classifier.h>
|
| | PersonClassifier () |
| | Constructor. More...
|
| |
| virtual | ~PersonClassifier () |
| | Destructor. More...
|
| |
| bool | loadSVMFromFile (const std::string &svm_filename) |
| | Load SVM parameters from a text file. More...
|
| |
| void | setSVM (int window_height, int window_width, std::vector< float > SVM_weights, float SVM_offset) |
| | Set trained SVM for person confidence estimation. More...
|
| |
| void | getSVM (int &window_height, int &window_width, std::vector< float > &SVM_weights, float &SVM_offset) |
| | Get trained SVM for person confidence estimation. More...
|
| |
| void | resize (PointCloudPtr &input_image, PointCloudPtr &output_image, int width, int height) |
| | Resize an image represented by a pointcloud containing RGB information. More...
|
| |
| void | copyMakeBorder (PointCloudPtr &input_image, PointCloudPtr &output_image, int xmin, int ymin, int width, int height) |
| | Copies an image and makes a black border around it, where the source image is not present. More...
|
| |
| double | evaluate (float height, float xc, float yc, PointCloudPtr &image) |
| | Classify the given portion of image. More...
|
| |
| double | evaluate (PointCloudPtr &image, Eigen::Vector3f &bottom, Eigen::Vector3f &top, Eigen::Vector3f ¢roid, bool vertical) |
| | Compute person confidence for a given PersonCluster. More...
|
| |
template<typename PointT>
class pcl::people::PersonClassifier< PointT >
Definition at line 53 of file person_classifier.h.
◆ PointCloud
template<typename PointT >
◆ PointCloudPtr
template<typename PointT >
◆ PersonClassifier()
template<typename PointT >
◆ ~PersonClassifier()
template<typename PointT >
◆ copyMakeBorder()
template<typename PointT >
Copies an image and makes a black border around it, where the source image is not present.
- Parameters
-
| [in] | input_image | A pointer to a pointcloud containing RGB information. |
| [out] | output_image | A pointer to the output pointcloud. |
| [in] | xmin | x coordinate of the top-left point of the bbox to copy from the input image. |
| [in] | ymin | y coordinate of the top-left point of the bbox to copy from the input image. |
| [in] | width | Output width. |
| [in] | height | Output height. |
Definition at line 177 of file person_classifier.hpp.
◆ evaluate() [1/2]
template<typename PointT >
Classify the given portion of image.
- Parameters
-
| [in] | height | The height of the image patch to classify, in pixels. |
| [in] | xc | The x-coordinate of the center of the image patch to classify, in pixels. |
| [in] | yc | The y-coordinate of the center of the image patch to classify, in pixels. |
| [in] | image | The whole image (pointer to a point cloud containing RGB information) containing the object to classify. |
- Returns
- The classification score given by the SVM.
Definition at line 212 of file person_classifier.hpp.
References pcl::people::HOG::compute().
◆ evaluate() [2/2]
template<typename PointT >
Compute person confidence for a given PersonCluster.
- Parameters
-
| [in] | image | The input image (pointer to a point cloud containing RGB information). |
| [in] | bottom | Theoretical bottom point of the cluster projected to the image. |
| [in] | top | Theoretical top point of the cluster projected to the image. |
| [in] | centroid | Theoretical centroid point of the cluster projected to the image. |
| [in] | vertical | If true, the sensor is considered to be vertically placed (portrait mode). |
- Returns
- The person confidence.
Definition at line 279 of file person_classifier.hpp.
◆ getSVM()
template<typename PointT >
Get trained SVM for person confidence estimation.
- Parameters
-
| [out] | window_height | Detection window height. |
| [out] | window_width | Detection window width. |
| [out] | SVM_weights | SVM weights vector. |
| [out] | SVM_offset | SVM offset. |
Definition at line 100 of file person_classifier.hpp.
◆ loadSVMFromFile()
template<typename PointT >
Load SVM parameters from a text file.
- Parameters
-
| [in] | svm_filename | Filename containing SVM parameters. |
- Returns
- true if SVM has been correctly set, false otherwise.
Definition at line 53 of file person_classifier.hpp.
◆ resize()
template<typename PointT >
Resize an image represented by a pointcloud containing RGB information.
- Parameters
-
| [in] | input_image | A pointer to a pointcloud containing RGB information. |
| [out] | output_image | A pointer to the output pointcloud. |
| [in] | width | Output width. |
| [in] | height | Output height. |
Definition at line 109 of file person_classifier.hpp.
◆ setSVM()
template<typename PointT >
Set trained SVM for person confidence estimation.
- Parameters
-
| [in] | window_height | Detection window height. |
| [in] | window_width | Detection window width. |
| [in] | SVM_weights | SVM weights vector. |
| [in] | SVM_offset | SVM offset. |
Definition at line 91 of file person_classifier.hpp.
◆ SVM_offset_
template<typename PointT >
◆ SVM_weights_
template<typename PointT >
◆ window_height_
template<typename PointT >
◆ window_width_
template<typename PointT >
The documentation for this class was generated from the following files: