Merge pull request #41 from NVIDIA-ISAAC-ROS/release-3.0

Isaac ROS 3.0.1

Author: jaiveersinghNV

README.md

@@ -7,28 +7,35 @@ NVIDIA-accelerated, deep learned model support for object detection including De
 
 ## Overview
 
-[Isaac ROS Object Detection](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_object_detection) contains an ROS 2 package to perform object
-detection. `isaac_ros_detectnet` provides a method for spatial
+[Isaac ROS Object Detection](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_object_detection) contains ROS 2 packages to perform object
+detection.
+`isaac_ros_rtdetr`, `isaac_ros_detectnet`, and `isaac_ros_yolov8` each provide a method for spatial
 classification using bounding boxes with an input image. Classification
-is performed by a GPU-accelerated
-[DetectNet](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tao/models/pretrained_detectnet_v2)
-model. The output prediction can be used by perception functions to
+is performed by a GPU-accelerated model of the appropriate architecture:
+
+- `isaac_ros_rtdetr`: [RT-DETR models](https://nvidia-isaac-ros.github.io/concepts/object_detection/rtdetr/index.html)
+- `isaac_ros_detectnet`: [DetectNet models](https://nvidia-isaac-ros.github.io/concepts/object_detection/detectnet/index.html)
+- `isaac_ros_yolov8`: [YOLOv8 models](https://nvidia-isaac-ros.github.io/concepts/object_detection/yolov8/index.html)
+
+The output prediction can be used by perception functions to
 understand the presence and spatial location of an object in an image.
 
 <div align="center"><a class="reference internal image-reference" href="https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/main/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_object_detection/isaac_ros_object_detection_nodegraph.png/"><img alt="image" src="https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/main/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_object_detection/isaac_ros_object_detection_nodegraph.png/" width="800px"/></a></div>
 
-`isaac_ros_detectnet` is used in a graph of nodes to provide a
+Each Isaac ROS Object Detection package is used in a graph of nodes to provide a
 bounding box detection array with object classes from an input image. A
-[DetectNet](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tao/models/pretrained_detectnet_v2)
-model is required to produce the detection array. Input images may need
-to be cropped and resized to maintain the aspect ratio and match the
-input resolution of DetectNet; image resolution may be reduced to
+trained model of the appropriate architecture is required to produce the detection array.
+
+Input images may need to be cropped and resized to maintain the aspect ratio and match the
+input resolution of the specific object detection model; image resolution may be reduced to
 improve DNN inference performance, which typically scales directly with
 the number of pixels in the image. `isaac_ros_dnn_image_encoder`
-provides a DNN encoder to process the input image into Tensors for the
-DetectNet model. Prediction results are clustered in the DNN decoder to
-group multiple detections on the same object. Output is provided as a
-detection array with object classes.
+provides DNN encoder utilities to process the input image into Tensors for the
+object detection models.
+Prediction results are decoded in model-specific ways,
+often involving clustering and thresholding to group multiple detections
+on the same object and reduce spurious detections.
+Output is provided as a detection array with object classes.
 
 DNNs have a minimum number of pixels that need to be visible on the
 object to provide a classification prediction. If a person cannot see
@@ -41,10 +48,6 @@ image, which provides 1K pixels for the person, and fail to detect the
 same person in the downscaled resolution, which only provides 0.25K
 pixels for the person.
 
-> [!Note]
-> DetectNet is similar to other popular object detection
-> models such as YOLOV3, FasterRCNN, and SSD, while being efficient at
-> detecting multiple object classes in large images.
 <div align="center"><a class="reference internal image-reference" href="https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/main/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_object_detection/isaac_ros_object_detection_example_bboxseg.png/"><img alt="image" src="https://media.githubusercontent.com/media/NVIDIA-ISAAC-ROS/.github/main/resources/isaac_ros_docs/repositories_and_packages/isaac_ros_object_detection/isaac_ros_object_detection_example_bboxseg.png/" width="800px"/></a></div>
 
 Object detection classifies a rectangle of pixels as containing an

gxf_isaac_detectnet/package.xml

@@ -21,7 +21,7 @@ SPDX-License-Identifier: Apache-2.0
 <?xml-model href="http://download.ros.org/schema/package_format3.xsd" schematypens="http://www.w3.org/2001/XMLSchema"?>
 <package format="3">
   <name>gxf_isaac_detectnet</name>
-  <version>3.0.0</version>
+  <version>3.0.1</version>
   <description>Detectnet GXF extension.</description>
 
   <maintainer email="[email protected]">Isaac ROS Maintainers</maintainer>

isaac_ros_detectnet/launch/isaac_ros_detectnet_isaac_sim.launch.py

@@ -48,10 +48,10 @@ def generate_launch_description():
                 'encoding_desired': 'rgb8',
         }],
         remappings=[
-            ('camera_info', 'front_stereo_camera/left_rgb/camerainfo'),
-            ('image', 'front_stereo_camera/left_rgb/image_raw'),
-            ('resize/camera_info', 'front_stereo_camera/left_rgb/camerainfo_resize'),
-            ('resize/image', 'front_stereo_camera/left_rgb/image_resize')]
+            ('camera_info', 'front_stereo_camera/left/camera_info'),
+            ('image', 'front_stereo_camera/left/image_rect_color'),
+            ('resize/camera_info', 'front_stereo_camera/left/camera_info_resize'),
+            ('resize/image', 'front_stereo_camera/left/image_resize')]
     )
 
     encoder_dir = get_package_share_directory('isaac_ros_dnn_image_encoder')
@@ -71,8 +71,8 @@ def generate_launch_description():
             'attach_to_shared_component_container': 'True',
             'component_container_name': 'detectnet_container/detectnet_container',
             'dnn_image_encoder_namespace': 'detectnet_encoder',
-            'image_input_topic': '/front_stereo_camera/left_rgb/image_resize',
-            'camera_info_input_topic': '/front_stereo_camera/left_rgb/camerainfo_resize',
+            'image_input_topic': '/front_stereo_camera/left/image_resize',
+            'camera_info_input_topic': '/front_stereo_camera/left/camera_info_resize',
             'tensor_output_topic': '/tensor_pub',
         }.items(),
     )
@@ -117,7 +117,7 @@ def generate_launch_description():
         package='isaac_ros_detectnet',
         executable='isaac_ros_detectnet_visualizer.py',
         name='detectnet_visualizer',
-        remappings=[('image', 'front_stereo_camera/left_rgb/image_resize')]
+        remappings=[('image', 'front_stereo_camera/left/image_resize')]
 
     )
 

isaac_ros_detectnet/package.xml

@@ -21,7 +21,7 @@ SPDX-License-Identifier: Apache-2.0
 <?xml-model href="http://download.ros.org/schema/package_format3.xsd" schematypens="http://www.w3.org/2001/XMLSchema"?>
 <package format="3">
   <name>isaac_ros_detectnet</name>
-  <version>3.0.0</version>
+  <version>3.0.1</version>
   <description>DetectNet model processing</description>
 
   <maintainer email="[email protected]">Isaac ROS Maintainers</maintainer>

isaac_ros_detectnet/scripts/setup_model.sh

@@ -74,7 +74,7 @@ function setup_model() {
   model_name_from_model_link=$(extract_model_name "$MODEL_LINK")
   echo "Model name from model link: $model_name_from_model_link"
   echo Creating Directory : ${ISAAC_ROS_WS}/isaac_ros_assets/models/$model_name_from_model_link/1
-  rm -rf ${ISAAC_ROS_WS}/isaac_ros_assets/models
+  rm -rf ${ISAAC_ROS_WS}/isaac_ros_assets/models/$model_name_from_model_link
   mkdir -p ${ISAAC_ROS_WS}/isaac_ros_assets/models/$model_name_from_model_link/1
   cd ${ISAAC_ROS_WS}/isaac_ros_assets/models/$model_name_from_model_link/1
   echo Downloading .etlt file from $MODEL_LINK
@@ -99,7 +99,6 @@ function setup_model() {
     -o $OUTPUT_LAYERS\
     $MODEL_FILE_NAME
   echo Copying .pbtxt config file to ${ISAAC_ROS_WS}/isaac_ros_assets/models/$model_name_from_model_link
-  cd /workspaces/isaac_ros-dev/src/isaac_ros_object_detection/isaac_ros_detectnet
   export ISAAC_ROS_DETECTNET_PATH=$(ros2 pkg prefix isaac_ros_detectnet --share)
   cp $ISAAC_ROS_DETECTNET_PATH/config/$CONFIG_FILE \
     ${ISAAC_ROS_WS}/isaac_ros_assets/models/$model_name_from_model_link/config.pbtxt

isaac_ros_rtdetr/launch/isaac_ros_rtdetr_isaac_sim.launch.py

@@ -79,8 +79,8 @@ def generate_launch_description():
             'disable_padding': True
         }],
         remappings=[
-            ('image', 'front_stereo_camera/left_rgb/image_raw'),
-            ('camera_info', 'front_stereo_camera/left_rgb/camerainfo')
+            ('image', 'front_stereo_camera/left/image_rect_color'),
+            ('camera_info', 'front_stereo_camera/left/camera_info')
         ]
     )
     pad_node = ComposableNode(

isaac_ros_rtdetr/package.xml

@@ -21,7 +21,7 @@ SPDX-License-Identifier: Apache-2.0
 <?xml-model href="http://download.ros.org/schema/package_format3.xsd" schematypens="http://www.w3.org/2001/XMLSchema"?>
 <package format="3">
   <name>isaac_ros_rtdetr</name>
-  <version>3.0.0</version>
+  <version>3.0.1</version>
   <description>RT-DETR model processing</description>
 
   <maintainer email="[email protected]">Isaac ROS Maintainers</maintainer>

isaac_ros_yolov8/package.xml

@@ -21,7 +21,7 @@
 <?xml-model href="http://download.ros.org/schema/package_format3.xsd" schematypens="http://www.w3.org/2001/XMLSchema"?>
 <package format="3">
   <name>isaac_ros_yolov8</name>
-  <version>3.0.0</version>
+  <version>3.0.1</version>
   <description>Isaac ROS YOLOv8 decoding</description>
 
   <maintainer email="[email protected]">Isaac ROS Maintainers</maintainer>