frame_process.py

import pickle
import numpy as np

def social_frame_preprocess():
    '''
    Preprocess the frames from the datasets.
    Convert values to pixel locations from millimeters
    obtain and store all frames data the actually used frames (as some are skipped), 
    the ids of all pedestrians that are present at each of those frames and the sufficient statistics.
    '''
    def collect_stats():
        ''' Collect the means and standard deviation of all (x, y) positions of the agents '''
        x_pos = []
        y_pos = []
        for agent_id in range(1, len(agents)):
            trajectory = [[] for _ in range(3)]
            traj = agents[agent_id]
            for step in traj:
                x_pos.append(step[1])
                y_pos.append(step[2])
        x_pos = np.asarray(x_pos)
        y_pos = np.asarray(y_pos)
        # takes the average over all points through all agents
        return [[np.mean(x_pos), np.std(x_pos)], [np.mean(y_pos), np.std(y_pos)]]
    
    allPedsInFrame = []
    Hfile = os.path.join(directory, "H.txt")
    obsfile = os.path.join(directory, "obsmat.txt")
    # Parse homography matrix.
    H = np.loadtxt(Hfile)
    Hinv = np.linalg.inv(H)
    # Parse pedestrian annotations.
    frames, pedsInFrame, agents = parse_annotations(Hinv, obsfile)
    allPedsInFrame.append(agents)
    framesContent = np.zeros((len(frames), 40, 3))
    # collect mean and std
    statistics = collect_stats()
    # collect the id, normalised x and normalised y of each agent's position
    for ind, agent_list in enumerate(pedsInFrame):
        pedsWithPos = []
        for agent_id in agent_list:
            traj = agents[agent_id]
            for step in traj:
                if step[0] == ind:
                    pedsWithPos.append([
                        agent_id,
                        (step[1] - statistics[0][0]) / statistics[0][1],
                        (step[2] - statistics[1][0]) / statistics[1][1]
                    ])
        framesContent[ind, 0:len(agent_list), :] = np.array(pedsWithPos)

    return framesContent, frames, allPedsInFrame, statistics