projection of GT on to the image. too many negatives.

[mdfaheem786]

Hi, great dataset for experimenting deep learning network for autonomous vehicles.

but while using the sdk for projection of GT on to images, got many negatives, is there a way to handle these negatives.

attached is one sample of projection ( 057 folder, 60.jpg - front camera)

thanking you in advances.

[mdfaheem786]

Here is my code, please kindly let me know where is the issue.

import pandaset from pandaset import geometry import numpy as np import cv2 from typing import List, Optional, Tuple import copy

import glob import json import os from typing import overload, List, TypeVar, Dict import pandas as pd import random from PIL import Image from python.pandaset.sensors import Intrinsics

random.seed(9876543210)

def dump_3d_bbox_on_image( coords, img, fpath, color: Optional[Tuple[int, int, int]] = None, thickness: float = 4, ) -> None:

canvas = img.copy()
canvas = cv2.cvtColor(canvas, cv2.COLOR_RGB2BGR)
coords = coords.astype(np.int32)
for index in range(coords.shape[0]):
    projected_points2d = coords[index]
    bbox = projected_points2d.tolist()
    cv2.line(canvas, bbox[0], bbox[1], color, thickness)
    cv2.line(canvas, bbox[0], bbox[4], color, thickness)
    cv2.line(canvas, bbox[0], bbox[3], color, thickness)
    cv2.line(canvas, bbox[1], bbox[2], color, thickness)
    cv2.line(canvas, bbox[1], bbox[5], color, thickness)
    cv2.line(canvas, bbox[2], bbox[3], color, thickness)
    cv2.line(canvas, bbox[2], bbox[6], color, thickness)
    cv2.line(canvas, bbox[3], bbox[7], color, thickness)
    cv2.line(canvas, bbox[4], bbox[7], color, thickness)
    cv2.line(canvas, bbox[4], bbox[5], color, thickness)
    cv2.line(canvas, bbox[5], bbox[6], color, thickness)
    cv2.line(canvas, bbox[6], bbox[7], color, thickness)
canvas = canvas.astype(np.uint8)
canvas = cv2.cvtColor(canvas, cv2.COLOR_BGR2RGB)

cv2.imwrite(fpath, canvas)
return

class CameraData: size: None def init(self, sze) -> None: self.size = sze return

if name == "main":

datasetPath = "/home/pandaset/"
out = "out"
numFolders = 4
numImgs = 5
allSeq = sorted(glob.glob(f'{datasetPath}/*/'))
seqrandidx = random.sample(range(0,len(allSeq)), numFolders)
# seq = "001"
front_camera_dir = "camera/front_camera/"
front_camera_dir = "camera/back_camera/"
front_camera_dir = "camera/front_right_camera/"
cuboids_dir = "annotations/cuboids/"
data_file_extension = "pkl.gz"

for idx in seqrandidx:
    seq = allSeq[idx]
    # seq = seq[:-4] + "057/"
    
    cuboidsFullPath = os.path.join(seq, cuboids_dir)
    frontFullPath = os.path.join(seq, front_camera_dir)
    lstfiles = sorted(glob.glob(f'{cuboidsFullPath}/*.{data_file_extension}'))

    imgrandidx = random.sample(range(0,len(lstfiles)), numImgs)
    for itemidx in imgrandidx:
        cubpath = lstfiles[itemidx]
        syncidx = cubpath.split("/")[-1]
        syncidx = syncidx[:-7]
        pklgzName = syncidx + ".jpg"
        imgpath = os.path.join(frontFullPath, pklgzName)
        ori_image = Image.open(imgpath)
        img = np.array(ori_image)
        cuboids0 = pd.read_pickle(cubpath)

        # remove nan values in the camera_used
        ori_cuboids0 = copy.deepcopy(cuboids0)
        cuboids0 = cuboids0[cuboids0["camera_used"] == -1]

        posepath = os.path.join(frontFullPath, "poses.json")
        intrinsicspath = os.path.join(frontFullPath, "intrinsics.json")
        with open(posepath, 'r') as f:
            pose = json.load(f)
        with open(intrinsicspath, 'r') as f:
            file_data = json.load(f)
            intrinsics = Intrinsics(
                fx=file_data['fx'],
                fy=file_data['fy'],
                cx=file_data['cx'],
                cy=file_data['cy'])
            
        box = [            
            cuboids0[  "position.x"], cuboids0[  "position.y"], cuboids0[  "position.z"],
            cuboids0["dimensions.x"], cuboids0["dimensions.y"], cuboids0["dimensions.z"],
            cuboids0["yaw"]
            ]
                
        intsyncidx = int(syncidx)

        lstProj2d = list()
        for index, row in cuboids0.iterrows():
                box = [
                    row[  "position.x"], row[  "position.y"], row[  "position.z"],
                    row["dimensions.x"], row["dimensions.y"], row["dimensions.z"],
                    row["yaw"]
                ]
                corners = geometry.center_box_to_corners(box)
            
                camera_data = CameraData((1920, 1080))

                projected_points2d, camera_points_3d, inner_indices = \
                    geometry.projection(
                        lidar_points=corners,                
                        # camera_data=None,
                        camera_data=camera_data,
                        camera_pose=pose[intsyncidx],
                        camera_intrinsics=intrinsics,
                        filter_outliers=True)  # False)  # True)  # False)
                projected_points2d = projected_points2d.tolist()
                if len(projected_points2d) == 8:
                    lstProj2d.append(projected_points2d)

        lstProj2d = np.asarray(lstProj2d)
        outname = out + "/"
        temp = imgpath[len(datasetPath):]
        temp = temp.split("/")
        for item in temp:
            outname += "_" + item
        print(f"outname - {outname}")
        dump_3d_bbox_on_image(coords=lstProj2d, img=img, fpath=outname, color=(0,0,255))

exit(0)

@pfmark - please kindly help me...

[william-ljz]

Please tell me, has it been resolved?