The Peoplenet Autonomous Mobile Robot (AMR) model described in this card detect one or more physical objects from three categories within an image and return a box around each object, as well as a category label for each object. Three categories of objects detected by these models are – persons, bags and faces.
This model is based on NVIDIA DetectNet_v2 detector with ResNet34 as feature extractor. This architecture, also known as GridBox object detection, uses bounding-box regression on a uniform grid on the input image. Gridbox system divides an input image into a grid which predicts four normalized bounding-box parameters (xc, yc, w, h) and confidence value per output class.
The raw normalized bounding-box and confidence detections needs to be post-processed by a clustering algorithm such as DBSCAN or NMS to produce final bounding-box coordinates and category labels.
This model was trained using the DetectNet_v2 entrypoint in TAO. The training algorithm optimizes the network to minimize the localization and confidence loss for the objects. The training is carried out in two phases. In the first phase, the network is trained without regularization.
PeopleNet AMR model was trained on a proprietary dataset with more than 3 million images and more than 8 million objects for person class. The training dataset consists of a mix of camera heights, crowd-density, and field-of view (FOV). Approximately two thirds of the training data consisted of images captured in a indoor and outdoor environments that are from a horizontal view point. For this case, the camera is typically set up at approximately 2 to 5 feet height, 90-degree angle and has wide field-of-view. We have also added approximately 45 thousand images with low-density scenes from a robot's point of view to improve the performance for use-cases where person object detection is needed at low heights.
Category | Number of Images | Number of Persons | Number of Bags | Number of Faces |
---|---|---|---|---|
Natural | 1920657 | 6592311 | 1811658 | 3032396 |
-- Robotics Subset | 43076 | 160806 | 40413 | 24109 |
Rotated | 1020163 | 1800844 | 291754 | 963805 |
Total | 3028550 | 8553961 | 2143825 | 4020310 |
The training dataset is created by labeling ground-truth bounding-boxes and categories by human labellers. Following guidelines were used while labelling the training data for NVIDIA PeopleNet AMR model. If you are looking to re-train with your own dataset, please follow the guideline below for highest accuracy.
PeopleNet AMR project labelling guidelines:
All objects that fall under one of the three classes (person, face, bag) in the image and are larger than the smallest bounding-box limit for the corresponding class (height >= 10px OR width >= 10px @1920x1080) are labeled with the appropriate class label.
If a person is carrying an object please mark the bounding-box to include the carried object as long as it doesn’t affect the silhouette of the person. For example, exclude a rolling bag if they are pulling it behind them and are distinctly visible as separate object. But include a backpack, purse etc. that do not alter the silhouette of the pedestrian significantly.
Occlusion: For partially occluded objects that do not belong a person class and are visible approximately 60% or are marked as visible objects with bounding box around visible part of the object. These objects are marked as partially occluded. Objects under 60% visibility are not annotated.
Occlusion for person class: If an occluded person’s head and shoulders are visible and the visible height is approximately 20% or more, then these objects are marked by the bounding box around the visible part of the person object. If the head and shoulders are not visible please follow the Occlusion guidelines in item 3 above.
Truncation: For an object other than a person that is at the edge of the frame with visibility of 60% or more visible are marked with the truncation flag for the object.
Truncation for person class: If a truncated person’s head and shoulders are visible and the visible height is approximately 20% or more mark the bounding box around the visible part of the person object. If the head and shoulders are not visible please follow the Truncation guidelines in item 5 above.
Each frame is not required to have an object.
The inference performance of PeopleNet AMR v0.1 model was measured against more than 15000 proprietary images across a variety of environments. The frames are high resolution images 1920x1080 pixels resized to 960x544 pixels before passing to the PeopleNet AMR detection model.
The true positives, false positives, false negatives are calculated using intersection-over-union (IOU) criterion greater than 0.5. The KPI for the evaluation data are reported in the table below. The FP16 Model is evaluated based on precision, recall and accuracy.
Content | Precision | Recall | Accuracy |
---|---|---|---|
Generic | 98.75 | 94.71 | 85.47 |
Office | 94.24 | 78.05 | 74.50 |
Robotics | 89.01 | 83.14 | 76.39 |
Extended Hands | 97.00 | 89.84 | 87.41 |
Extended-hands (IOU > 0.8) | 91.50 | 84.76 | 78.57 |
People (IOU > 0.8) | 82.56 | 77.62 | 66.69 |
Robotics (IOU > 0.8) | 84.81 | 80.28 | 70.91 |
These models need to be used with NVIDIA Hardware and Software. For Hardware, the models can run on any NVIDIA GPU including NVIDIA Jetson devices. These models can only be used with Train Adapt Optimize (TAO) Toolkit or TensorRT.
The primary use case intended for these models is detecting people in a color (RGB) image. The model can be used to detect people from photos and videos by using appropriate video or image decoding and pre-processing. As a secondary use case the model can also be used to detect bags and faces from images or videos. However, these additional classes are not the main intended use for these models.
There are two flavors of these models:
The trainable or unpruned
models intended for training using TAO Toolkit and the user's own dataset. This can provide high fidelity models that are adapted to the use case. The Jupyter notebook available as a part of TAO container can be used to re-train.
RGB Image of dimensions: 960 X 544 X 3 (W x H x C) Channel Ordering of the Input: NCHW, where N = Batch Size, C = number of channels (3), H = Height of images (544), W = Width of the images (960) Input scale: 1/255.0 Mean subtraction: None
Category labels (person, bag, face) and bounding-box coordinates for each detected object in the input image.
In order, to use these models as a pretrained weights for transfer learning, please use the snippet below as template for the model_config
component of the experiment spec file to train a DetectNet_v2 model. For more information on the experiment spec file, please refer to the TAO Toolkit User Guide.
model_config {
num_layers: 34
pretrained_model_file: "/path/to/the/model.tlt"
use_batch_norm: true
objective_set {
bbox {
scale: 35.0
offset: 0.5
}
cov {
}
}
training_precision {
backend_floatx: FLOAT32
}
arch: "resnet"
all_projections: true
}
NVIDIA PeopleNet AMR model were trained to detect objects larger than 10x10 pixels. Therefore it may not be able to detect objects that are smaller than 10x10 pixels.
When objects are occluded or truncated such that less than 20% of the object is visible, they may not be detected by the PeopleNet AMR model. For people class objects, the model will detect occluded people as long as head and shoulders are visible. However if the person’s head and/or shoulders are not visible, the object might not be detected unless more than 60% of the person is visible.
The PeopleNet AMR model were trained on RGB images in good lighting conditions. Therefore, images captured in dark lighting conditions or a monochrome image or IR camera image may not provide good detection results.
The PeopleNet AMR models were not trained on fish-eye lense cameras. Therefore, the models may not perform well for warped images and images that have a lot of blur.
Although bag and face class are included in the model, the accuracy of these classes will be much lower than people class. Some re-training will be required on these classes to improve accuracy.
License to use these models is covered by the Model EULA. By downloading the unpruned or pruned version of the model, you accept the terms and conditions of these licenses.
NVIDIA PeopleNet AMR model detects faces. However, no additional information such as race, gender, and skin type about the faces is inferred.
Training and evaluation dataset mostly consists of North American content. An ideal training and evaluation dataset would additionally include content from other geographies.
NVIDIA’s platforms and application frameworks enable developers to build a wide array of AI applications. Consider potential algorithmic bias when choosing or creating the models being deployed. Work with the model’s developer to ensure that it meets the requirements for the relevant industry and use case; that the necessary instruction and documentation are provided to understand error rates, confidence intervals, and results; and that the model is being used under the conditions and in the manner intended.