Advances the state vector and returns the predicted bounding box estimate.

Extracts keypoints This method extracts keypoints for feature matching based on a specified mode: - "sift": use r

Estimates fundamental matrix

Disable recording mode and reset data structures

Params: dets - a numpy array of detections in the format [[x1,y1,x2,y2,score],[x1,y1,x2,y2,score],...] Requires: this metho

Capture a new frame from the input device :return: (success, frame) Whether acquiring was successful and current frame.

Capture a new frame from the input device :return: (success, frame) Whether acquiring was successful and current frame.

Capture a new frame from the input device :return: (success, frame) Whether acquiring was successful and current frame.

Capture a new frame from the input device :return: (success, frame) Whether acquiring was successful and current frame.

Capture a new frame from the input device :return: (success, frame) Whether acquiring was successful and current frame.

Calculate the log-magnitude of the Fourier spectrum of a single-channel image. This image could be a regular grayscale image, or a single

GTSRB_Final_Training_Images.zip

Helper method to draw epipolar lines and features

Extracts keypoints via optic flow

Finds the [R|t] camera matrix

Estimates essential matrix based on fundamental matrix

Aligns a head region using affine transformations This method preprocesses an extracted head region by rotating and scaling i

Takes a bounding box in the form [x1,y1,x2,y2] and returns z in the form [x,y,s,r] where x,y is the centre of the box and s is the scale/ar

Takes a bounding box in the centre form [x,y,s,r] and returns it in the form [x1,y1,x2,y2] where x1,y1 is the top left and x2,y2 is the botto

Performs face detection This method detects faces in an RGB input image. The method returns True upon success (else False), d

Detects and tracks an object of interest in a video frame This method detects and tracks an object of interest (of which a SU

Do minimum pre-processing 1. resize to UNIFORM_SIZE 2. scale to (0, 1) range 3. subtract the mean of all pixel values

Extracts keypoints via sift descriptors

Determines whether point correspondences are in front of both images

Advance the algorithm by a single frame certain targets are discarded: - targets that are too small - targets that

Angle in radians between two vectors This method returns the angle (in radians) between two array-like vectors using the cross-produc

Assigns detections to tracked object (both represented as bounding boxes) Returns 3 lists of matches, unmatched_detections and unmatched_tra

Augment custom layout elements to the GUI. This method is called in the class constructor, after initializing common parameters. Eve

Augment custom layout elements to the GUI. This method is called in the class constructor, after initializing common parameters. Eve

Augment custom layout elements to the GUI. This method is called in the class constructor, after initializing common parameters. Eve

Augment custom layout elements to the GUI. This method is called in the class constructor, after initializing common parameters. Eve

Augment custom layout elements to the GUI. This method is called in the class constructor, after initializing common parameters. Eve

Plot the magnitude spectrum This method calculates the magnitude spectrum of the image passed to the class constructor. :retur

Convert degrees to radians This method converts an angle in radians e[0,2*np.pi) into degrees e[0,360)

Detects corner points in an input (query) image This method finds the homography matrix to go from the template (train) image to the

Detects the number of extended fingers This method determines the number of extended fingers based on a contour and convexity defects

Visualizes a list of good matches This function visualizes a list of good matches. It is only required in OpenCV releases that do not

Find hull defects This method finds all defects in the hull of a segmented arm region. :param segment: a binary image (mask)

Generate the proto-objects map of an RGB image Proto-objects are saliency hot spots, generated by thresholding the saliency map. :p

Returns a saliency map This function generates a saliency map for the image that was passed to the class constructor. :returns: gra

Featurize using histogram of gradients. For each image: 1. resize all images to have the same (usually smaller size) 2. Calc

Computes IUO between two bboxes in the form [x1,y1,x2,y2]

Loads pair of images This method loads the two images for which the 3D scene should be reconstructed. The two images should s

Feature matching between train and query image This method finds matches between the descriptor of an input (query) frame and

Plots optic flow field This method plots the optic flow between the first and second image.

Plots 3D point cloud This method generates and plots a 3D point cloud of the recovered 3D scene. :param feat_mod

Plot the power spectrum of image

Process the frame of the camera (or other capture device) :param frame_rgb: Image to process in rgb format, of shape (H, W, 3) :retur