BatchParameters Class Reference

Class containing a set of parameters for batch object detection. More...

Functions

BatchParameters __cinit__ (self, enable=False, id_retention_time=240, batch_duration=2.0)
 Default constructor. More...
 
bool enable (self)
 Whether to enable the batch option in the object detection module. More...
 
float id_retention_time (self)
 Max retention time in seconds of a detected object. More...
 
float latency (self)
 Trajectories will be output in batch with the desired latency in seconds. More...
 

Detailed Description

Class containing a set of parameters for batch object detection.

The default constructor sets all parameters to their default settings.

Note
Parameters can be adjusted by the user.

Functions

◆ __cinit__()

BatchParameters __cinit__ (   self,
  enable = False,
  id_retention_time = 240,
  batch_duration = 2.0 
)

Default constructor.

All the parameters are set to their default values. param enable : Activates enable param id_retention_time : Chosen id_retention_time param batch_duration : Chosen latency

◆ enable()

bool enable (   self)

Whether to enable the batch option in the object detection module.

Batch queueing system provides:

  • deep-learning based re-identification
  • trajectory smoothing and filtering

Default: False

Note
To activate this option, enable must be set to True.

◆ id_retention_time()

float id_retention_time (   self)

Max retention time in seconds of a detected object.

After this time, the same object will mostly have a different id.

◆ latency()

float latency (   self)

Trajectories will be output in batch with the desired latency in seconds.

During this waiting time, re-identification of objects is done in the background.

Note
Specifying a short latency will limit the search (falling in timeout) for previously seen object ids but will be closer to real time output.
Specifying a long latency will reduce the change of timeout in re-identification but increase difference with live output.