ReIDPostprocessing
Attach reid to bounding boxes based on embeddings
This module provides a pipeline element to attach reid to person bounding boxes based on their embeddings.
Databases (<e-database>
) currently supported are:
- Redis (
redis
)
Examples:
REST API:
WIP
Configuration File:
```yaml
elements:
- name: infer
args:
model: person-v2
mode: a
- name: demux
- name: reid-preprocessing
- name: infer
args:
model: reid
mode: a
- name: mux
- name: reid-postprocessing
sources:
- address: videos/sample.mp4
type: file
```
ReIDPostprocessing Objects
class ReIDPostprocessing(Element)
Search for an identification in the embedding database and assign it to the detection.
Attributes:
name
str - The name of the element
Examples:
```python
ele = ReIDPostprocessing()
```
process
def process(meta: PipelineMetadata)
Process the detections and assign the identification to the detection.
This is the main function for the element. It takes the detection and searches for the identification in the embedding database. If the identification string is found, the detection is assigned the identification.
Arguments:
meta
PipelineMetadata - The metadata to process.
Returns:
meta
PipelineMetadata - The processed metadata.
Examples:
```python
meta = ReIDPostprocessing().process(meta)
```