Models
PeopleSegNet

PeopleSegNet

Logo for PeopleSegNet
Features
Description
1 class instance segmentation network to detect and segment instances of people in an image.
Publisher
-
Latest Version
deployable_v2.0.2
Modified
August 19, 2024
Size
70.54 MB

PeopleSegNet Model Card

Description:

PeopleSegNet detects persons in an image. This model is ready for commercial use.

References:

Citations

  • K. He, G. Gkioxari, P. Dollar, and R. Girshick. Mask RCNN. In ICCV, 2017. 1, 2, 4

Using TAO Pre-trained Models

Model Architecture:

Architecture Type: Convolution Neural Network (CNN)
Network Architecture: MaskRCNN + ResNet50

Input:

Input Type(s): Images
Input Format(s): Red, Green, Blue (RGB)
Input Parameters: 3D
Other Properties Related to Input: RGB Fixed Resolution: 960 X 576 X 3 (W x H x C); No minimum bit depth, alpha, or gamma.

Output:

Output Type(s): Label(s), Bounding-Box(es), Segmentation Mask(s)
Output Format: Label: Text String(s); Bounding Box: (x-coordinate, y-coordinate, width, height), Segmentation Mask: 2D
Other Properties Related to Output: Category Label(s): Person, Bounding Box Coordinates, Confidence Scores, Segmentation Mask

Software Integration:

Runtime Engine(s):

  • TAO - 5.2
  • DeepStream - 6.1

Supported Hardware Architecture(s):

  • Ampere
  • Jetson
  • Hopper
  • Lovelace
  • Pascal
  • Turing
  • Volta

Supported Operating System(s):

  • Linux
  • Linux 4 Tegra

Model Version(s):

  • trainable_v2.1 - ResNet50 based pre-trained model.
  • deployable_v2.0.2 - ResNet50 based model deployable to deepstream.

Training & Evaluation:

Training Dataset:

Data Collection Method by dataset:

  • Automatic/Sensors

Labeling Method by dataset:

  • Human

Properties:
Proprietary dataset of more than 5 million people. The training dataset consists of a mix of camera heights, crowd-density, and field-of view (FOV) for multiple camera types across all samples. Approximately half of the training data consisted of images captured in an indoor office environment.

Object
Environment Images Persons
5ft Indoor 108,692 1,060,960
5ft Outdoor 206,912 166,8250
10ft Indoor (Office close FOV) 413,270 4,577,870
10ft Outdoor 18,321 178,817
20ft Indoor 104,972 1,079,550
20ft Outdoor 24,783 59,623
Total 876,950 8,625,070
Training Data Ground-truth Labeling Guidelines

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 PeopleSegNet model. If you are looking to re-train with your own dataset, please follow the guideline below for highest accuracy.

PeopleSegNet project labelling guidelines:

  1. 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.

  2. 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.

  3. 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.

  4. 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.

  5. 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.

  6. 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.

  7. Each frame is not required to have an object.

Evaluation Dataset:

Data Collection Method by dataset:

  • Automatic/Sensors

Labeling Method by dataset:

  • Human

Properties:
42000 proprietary images of people across a variety of environments with multiple camera types.

Methodology and KPI

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. Model is evaluated based on precision, recall and accuracy.

Model ResNet 50
Content Precision Recall Accuracy
5ft 93.69 90.36 85.45
10ft 96.13 76.22 73.95
20ft 97.58 91.88 90.52
Office use-case 88.31 94.52 86.00

Inference:

Engine: Tensor(RT)
Test Hardware:

  • Jetson AGX Xavier
  • Xavier NX
  • Orin
  • Orin NX
  • NVIDIA T4
  • Ampere GPU
  • A2
  • A30
  • L4
  • T4
  • DGX H100
  • DGX A100
  • DGX H100
  • L40
  • JAO 64GB
  • Orin NX16GB
  • Orin Nano 8GB

The inference is run on the provided pruned models at INT8 precision. On the Jetson Nano FP16 precision is used. The inference performance is run using trtexec on Jetson Nano, AGX Xavier, Xavier NX and NVIDIA T4 GPU. The Jetson devices are running at Max-N configuration for maximum GPU frequency. The performance shown here is the inference only performance. The end-to-end performance with streaming video data might slightly vary depending on other bottlenecks in the hardware and software.

Platform FPS
Nano 0.6
Xavier NX 8.5
AGX Xavier 12.2
T4 40

How to use this model

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, DeepStream SDK or TensorRT.

Primary use case intended for the model is detecting and segmenting people in a color (RGB) image. The model can be used to detect and segment people from photos and videos by using appropriate video or image decoding and pre-processing.

The model is intended for training using Transfer Learning Toolkit with the user's own dataset or using it as it is. This can provide high fidelity models that are adapted to the use case. The Jupyter notebook available as a part of TLT container can be used to re-train.

The model is encrypted and will only operate with the following key:

  • Model load key: nvidia_tlt

Please make sure to use this as the key for all TAO commands that require a model load key.

Instructions to use unpruned model with TAO

In order, to use these models as a pretrained weights for transfer learning, please use the snippet below as template for the maskrcnn_config component of the experiment spec file to train a MaskRCNN model. For more information on the experiment spec file, please refer to the TAO Toolkit User Guide.

maskrcnn_config {
  nlayers: 50
  arch: "resnet"
  gt_mask_size: 112
  freeze_blocks: "[0]"
  freeze_bn: True
  # Region Proposal Network
  rpn_positive_overlap: 0.7
  rpn_negative_overlap: 0.3
  rpn_batch_size_per_im: 256
  rpn_fg_fraction: 0.5
  rpn_min_size: 0.

  # Proposal layer.
  batch_size_per_im: 512
  fg_fraction: 0.25
  fg_thresh: 0.5
  bg_thresh_hi: 0.5
  bg_thresh_lo: 0.

  # Faster-RCNN heads.
  fast_rcnn_mlp_head_dim: 1024
  bbox_reg_weights: "(10., 10., 5., 5.)"

  # Mask-RCNN heads.
  include_mask: True
  mrcnn_resolution: 28

  # training
  train_rpn_pre_nms_topn: 2000
  train_rpn_post_nms_topn: 1000
  train_rpn_nms_threshold: 0.7

  # evaluation
  test_detections_per_image: 100
  test_nms: 0.5
  test_rpn_pre_nms_topn: 1000
  test_rpn_post_nms_topn: 1000
  test_rpn_nms_thresh: 0.7

  # model architecture
  min_level: 2
  max_level: 6
  num_scales: 1
  aspect_ratios: "[(1.0, 1.0), (1.4, 0.7), (0.7, 1.4)]"
  anchor_scale: 8

  # localization loss
  rpn_box_loss_weight: 1.0
  fast_rcnn_box_loss_weight: 1.0
  mrcnn_weight_loss_mask: 1.0
}

Instructions to deploy these models with DeepStream

To create the entire end-to-end video analytic application, deploy these models with DeepStream SDK. DeepStream SDK is a streaming analytic toolkit to accelerate building AI-based video analytic applications. DeepStream supports direct integration of these models into the deepstream sample app.

To deploy these models with DeepStream 6.1, please follow the instructions below:

Download and install DeepStream SDK. The installation instructions for DeepStream are provided in DeepStream development guide. The config files for the purpose-built models are located in:

/opt/nvidia/deepstream is the default DeepStream installation directory. This path will be different if you are installing in a different directory.

You will need 2 config files and 1 label file. These files are provided in NVIDIA-AI-IOT.

deepstream_app_source1_peoplesegnet.txt - Main config file for DeepStream app
pgie_peopleSegNetv2_tao_config.txt - File to configure inference settings 
peopleSegNet_labels.txt - Label file with 1 class

Key Parameters in pgie_peopleSegNetv2_tao_config.txt

tlt-model-key=nvidia_tlt
tlt-encoded-model=../../models/peopleSegNet/V2/peoplesegnet_resnet50.etlt
model-engine-file=../../models/peopleSegNet/V2/peoplesegnet_resnet50.etlt_b1_gpu0_int8.engine
network-type=3 ## 3 is for instance segmentation network
labelfile-path=./peopleSegNet_labels.txt
int8-calib-file=../../models/peopleSegNet/V2/peoplesegnet_resnet50_int8.txt
infer-dims=3;576;960
num-detected-classes=2

Run deepstream-app:

deepstream-app -c deepstream_app_source1_peoplesegnet.txt

Documentation to deploy with DeepStream is provided in "Deploying to DeepStream" chapter of TAO User Guide.

Technical blogs

Suggested reading

Ethical Considerations:

Training and evaluation dataset is sourced from North America. More inclusive training and evaluation dataset would include content from other parts of the world.

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. For more detailed information on ethical considerations for this model, please see the Model Card++ Promise and the Explainability, Bias, Safety & Security, and Privacy Subcards.