The categories problem during training the VisDrone dataset

[Cuogeihong]

While training the RetinaNet baseline using your splited VisDrone dataset, I find the processed dataset has only 9 categories. In the visdrone/data_prepare.py, I find these codes

    ann_dict = {}
    ann_dict['categories'] = [
        {'supercategory': 'things', 'id': 1, 'name': 'people'},
        {'supercategory': 'things', 'id': 2, 'name': 'bicycle'},
        {'supercategory': 'things', 'id': 3, 'name': 'car'},
        {'supercategory': 'things', 'id': 4, 'name': 'van'},
        {'supercategory': 'things', 'id': 5, 'name': 'truck'},
        {'supercategory': 'things', 'id': 6, 'name': 'tricycle'},
        {'supercategory': 'things', 'id': 7, 'name': 'awning-tricycle'},
        {'supercategory': 'things', 'id': 8, 'name': 'bus'},
        {'supercategory': 'things', 'id': 9, 'name': 'motor'}
    ]
    ann_dict['images'] = images
    ann_dict['annotations'] = annotations
    with open(new_label_json, 'w') as outfile:
        json.dump(ann_dict, outfile)

Does that mean the people and pedestrian categories are merged? However, I can't find the merge part, the label's category_id seems to be exactly the same as the category_id from annotations‘ txt file. Maybe there exist some mistakes?