chore: update documentation

Signed-off-by: Barış Zeren <bzeren1819@gmail.com>

README.md

@@ -62,7 +62,88 @@ You can add your prompts as dictionaries under the `prompts` key. Each dictionar
 }
 ```
 
-Also, you should set your configuration in the configuration files under `config` folder according to the usage.
+You should set your configuration in the configuration files under `config` folder according to the usage.
+Following instructions will guide you to set each configuration file.
+
+**`config/anonymize_with_unified_model.yaml`**
+
+```yaml
+rosbag:
+  input_bag_path: "path/to/input.bag" # Path to the input ROS2 bag file with 'mcap' or 'sqlite3' extension
+  output_bag_path: "path/to/output/folder" # Path to the output ROS2 bag folder
+  output_save_compressed_image: True # Save images as compressed images (True or False)
+  output_storage_id: "sqlite3" # Storage id for the output bag file (`sqlite3` or `mcap`)
+
+grounding_dino:
+  box_threshold: 0.1 # Threshold for the bounding box (float)
+  text_threshold: 0.1 # Threshold for the text (float)
+  nms_threshold: 0.1 # Threshold for the non-maximum suppression (float)
+
+open_clip:
+  score_threshold: 0.7 # Validity threshold for the OpenCLIP model (float
+
+yolo:
+  confidence: 0.15 # Confidence threshold for the YOLOv8 model (float)
+
+bbox_validation:
+  iou_threshold: 0.9 # Threshold for the intersection over union (float), if the intersection over union is greater than this threshold, the object will be selected as inside the validation prompt
+
+blur:
+  kernel_size: 31 # Kernel size for the Gaussian blur (int)
+  sigma_x: 11 # Sigma x for the Gaussian blur (int)
+```
+
+**`config/yolo_create_dataset.yaml`**
+
+```yaml
+rosbag:
+  input_bags_folder: "path/to/input/folder" # Path to the input ROS2 bag files folder
+
+dataset:
+  output_dataset_folder: "path/to/output/folder" # Path to the output dataset folder
+  output_dataset_subsample_coefficient: 25 # Subsample coefficient for the dataset (int)
+
+grounding_dino:
+  box_threshold: 0.1 # Threshold for the bounding box (float)
+  text_threshold: 0.1 # Threshold for the text (float)
+  nms_threshold: 0.1 # Threshold for the non-maximum suppression (float)
+
+open_clip:
+  score_threshold: 0.7 # Validity threshold for the OpenCLIP model (float
+
+bbox_validation:
+  iou_threshold: 0.9 # Threshold for the intersection over union (float), if the intersection over union is greater than this threshold, the object will be selected as inside the validation prompt
+```
+
+**`config/yolo_train.yaml`**
+
+```yaml
+dataset:
+  input_dataset_yaml: "path/to/input/data.yaml" # Path to the config file of the dataset, which is created in the previous step
+
+yolo:
+  epochs: 100 # Number of epochs for the YOLOv8 model (int)
+  model: 'yolov8x.pt' # Select the base model for YOLOv8 ('yolov8x.pt' 'yolov8l.pt', 'yolov8m.pt', 'yolov8n.pt')
+```
+
+**`config/yolo_anonymize.yaml`**
+
+```yaml
+rosbag:
+  input_bag_path: "path/to/input.bag" # Path to the input ROS2 bag file with 'mcap' or 'sqlite3' extension
+  output_bag_path: "path/to/output/folder" # Path to the output ROS2 bag folder
+  output_save_compressed_image: True # Save images as compressed images (True or False)
+  output_storage_id: "sqlite3" # Storage id for the output bag file (`sqlite3` or `mcap`)
+
+yolo:
+  model: "path/to/yolo/model" # Path to the trained YOLOv8 model file (`.pt` extension) (you can download the pre-trained model from releases)
+  config_path: "path/to/input/data.yaml" # Path to the config file of the dataset, which is created in the previous step
+  confidence: 0.15 # Confidence threshold for the YOLOv8 model (float)
+
+blur:
+  kernel_size: 31 # Kernel size for the Gaussian blur (int)
+  sigma_x: 11 # Sigma x for the Gaussian blur (int)
+```
 
 ### Usage
 
@@ -71,7 +152,9 @@ The tool provides two options to anonymize images in rosbags.
 **Option 1: Anonymize with Unified Model**
 
 You should provide a single rosbag and tool anonymize images in rosbag with a unified model.
-The model is a combination of GroundingDINO, OpenCLIP and SegmentAnything.
+The model is a combination of GroundingDINO, OpenCLIP, YOLOv8 and SegmentAnything.
+If you don't want to use pre-trained YOLOv8 model, you can follow the instructions in the second option to train your 
+own YOLOv8 model.
 
 You should set your configuration in `config/anonymize_with_unified_model.yaml` file.
 
@@ -83,7 +166,7 @@ python3 main.py config/anonymize_with_unified_model.yaml --anonymize_with_unifie
 
 <ins>Step 1:</ins> Create an initial dataset with the unified model.
 You can provide multiple rosbags to create a dataset.
-You should set your configuration in `config/create_dataset_with_unified_model.yaml` file.
+You should set your configuration in `config/yolo_create_dataset.yaml` file.
 After running the following command, the tool will create a dataset in YOLO format.
 
 ``` shell
@@ -108,7 +191,11 @@ python3 main.py config/yolo_train.yaml --yolo_train
 ```
 
 <ins>Step 5:</ins> Anonymize images in rosbags with the trained YOLOv8 model.
-You should set your configuration in `config/yolo_anonymize.yaml` file.
+You should set your configuration in `config/yolo_anonymize.yaml` file. 
+If you want to anonymize your ROS2 bag file with only YOLOv8 model,
+you should use following command.
+But we recommend to use the unified model for better results.
+You can follow the `Option 1` for the unified model with the YOLOv8 model trained by you.
 
 ``` shell
 python3 main.py config/yolo_anonymize.yaml --yolo_anonymize

autoware_rosbag2_anonymizer/tools/anonymize_with_unified_model.py

@@ -20,7 +20,7 @@
 def anonymize_with_unified_model(config_data, json_data, device) -> None:
     reader = RosbagReader(config_data["rosbag"]["input_bag_path"], 1)
     writer = RosbagWriter(
-        config_data["rosbag"]["output_bag_paht"],
+        config_data["rosbag"]["output_bag_path"],
         config_data["rosbag"]["output_save_compressed_image"],
         config_data["rosbag"]["output_storage_id"],
     )

autoware_rosbag2_anonymizer/tools/yolo_anonymize.py

@@ -16,7 +16,7 @@
 
 
 def yolo_anonymize(config_data, json_data, device) -> None:
-    
+
     yolo_model_path = config_data["yolo"]["model"]
     yolo_confidence = config_data["yolo"]["confidence"]
     yolo_config_path = config_data["yolo"]["config_path"]
@@ -35,7 +35,7 @@ def yolo_anonymize(config_data, json_data, device) -> None:
     # Create rosbag reader and rosbag writer
     reader = RosbagReader(config_data["rosbag"]["input_bag_path"], 1)
     writer = RosbagWriter(
-        config_data["rosbag"]["output_bag_paht"],
+        config_data["rosbag"]["output_bag_path"],
         config_data["rosbag"]["output_save_compressed_image"],
         config_data["rosbag"]["output_storage_id"],
     )
@@ -58,7 +58,7 @@ def yolo_anonymize(config_data, json_data, device) -> None:
                 config_data["blur"]["kernel_size"],
                 config_data["blur"]["sigma_x"],
             )
-            
+
             # Debug ------------------
             # bounding_box_annotator = sv.BoundingBoxAnnotator()
             # annotated_image = bounding_box_annotator.annotate(

autoware_rosbag2_anonymizer/tools/yolo_create_dataset.py

@@ -37,23 +37,25 @@ def yolo_create_dataset(config_data, json_data, device) -> None:
     ANNOTATIONS_DIRECTORY_PATH = os.path.join(DATASET_DIR_PATH, "annotations")
     IMAGES_DIRECTORY_PATH = os.path.join(DATASET_DIR_PATH, "images")
     DATA_YAML_PATH = os.path.join(DATASET_DIR_PATH, "data.yaml")
-    
+
     # Create folders if it is not exist
     os.makedirs(DATASET_DIR_PATH, exist_ok=True)
     os.makedirs(ANNOTATIONS_DIRECTORY_PATH, exist_ok=True)
     os.makedirs(IMAGES_DIRECTORY_PATH, exist_ok=True)
-    
+
     # Declare counter variable for naming
     IMAGE_COUNTER = 0
-    SUBSAMPLE_COEFFICIENT = config_data["dataset"]["output_dataset_subsample_coefficint"]
-
+    SUBSAMPLE_COEFFICIENT = config_data["dataset"][
+        "output_dataset_subsample_coefficient"
+    ]
+
     for rosbag2_path in rosbag2_paths:
         reader = RosbagReader(rosbag2_path, SUBSAMPLE_COEFFICIENT)
-        
+
         for i, (msg, is_image) in enumerate(reader):
             if not is_image:
                 continue
-            
+
             # Convert image msg to cv.Mat
             image = image = cv_bridge.CvBridge().compressed_imgmsg_to_cv2(msg.data)
 
@@ -76,9 +78,9 @@ def yolo_create_dataset(config_data, json_data, device) -> None:
                 lines=lines,
                 file_path=f"{ANNOTATIONS_DIRECTORY_PATH}/image{IMAGE_COUNTER}.txt",
             )
-            
+
             IMAGE_COUNTER += 1
-            
+
             # box_annotator = sv.BoxAnnotator()
             # labels = [
             #     f"{DETECTION_CLASSES[class_id]} {confidence:0.2f}"
@@ -93,7 +95,7 @@ def yolo_create_dataset(config_data, json_data, device) -> None:
 
             # cv2.imshow("debug", image)
             # cv2.waitKey(1)
-            
+
     data = {"names": DETECTION_CLASSES, "nc": len(DETECTION_CLASSES)}
     with open(DATA_YAML_PATH, "w") as yaml_file:
-        yaml.dump(data, yaml_file, default_flow_style=False)
+        yaml.dump(data, yaml_file, default_flow_style=False)

config/anonymize_with_unified_model.yaml

@@ -1,6 +1,6 @@
 rosbag:
   input_bag_path: '/home/bzeren/projects/labs/data/rosbags/rosbag2_2024_03_22-18_27_21/rosbag2_2024_03_22-18_27_21_0-001.mcap'
-  output_bag_paht: '/home/bzeren/projects/labs/data/rosbags/rosbag2_2024_03_22-18_27_21/output'
+  output_bag_path: '/home/bzeren/projects/labs/data/rosbags/rosbag2_2024_03_22-18_27_21/output'
   output_save_compressed_image: True
   output_storage_id: 'sqlite3' # 'sqlite3' or 'mcap'
 grounding_dino:

config/yolo_anonymize.yaml

@@ -1,6 +1,6 @@
 rosbag:
   input_bag_path: '/media/bzeren/PortableSSD/YTU-DATA/rosbag2-anonymizer/rosbag2_2024_05_13-15_36_03/rosbag2_2024_05_13-15_36_03_0.db3'
-  output_bag_paht: '/home/bzeren/projects/labs/data/rosbags/rosbag2_2024_03_22-18_27_21/output'
+  output_bag_path: '/home/bzeren/projects/labs/data/rosbags/rosbag2_2024_03_22-18_27_21/output'
   output_save_compressed_image: True
   output_storage_id: 'sqlite3' # 'sqlite3' or 'mcap'
 yolo:

config/yolo_create_dataset.yaml

@@ -2,7 +2,7 @@ rosbag:
   input_bags_folder: '/media/bzeren/PortableSSD/YTU-DATA/rosbag2-anonymizer'
 dataset:
   output_dataset_folder: '/media/bzeren/PortableSSD/YTU-DATA/rosbag2-anonymizer/dataset'
-  output_dataset_subsample_coefficint: 25
+  output_dataset_subsample_coefficient: 25
 grounding_dino:
   config_path: './GroundingDINO_SwinB.cfg.py'
   checkpoint_path: './groundingdino_swinb_cogcoor.pth'

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "autoware_rosbag2_anonymizer"
-version = "1.0.0"
+version = "0.0.0"
 dependencies = [
   "cv_bridge",
   "huggingface_hub",