HUSKYLENS 2 Fall Detection Function Description

1.Introduction to Fall Detection

In the Fall Detection function, HUSKYLENS 2 can detect whether a person has fallen in the image and draw a bounding box around the fallen person.

2.Fall Detection Instructions

In this section, we will learn how to use the Fall Detection function of HUSKYLENS 2 to recognize fall events in the frame.

2.1 Select the Fall Detection Function

Power on HUSKYLENS 2. After it starts successfully, locate and select the Fall Detection function.

2.2 Observe Fall Detection Effect

Point the HUSKYLENS 2 camera at an image of a person who has fallen. Observe the screen of HUSKYLENS 2; a bounding box will appear in the frame to mark the fall event. In the top-left corner of the box, the confidence level and a unified ID—'ID1'—are displayed.

The fall detection function does not require learning. When multiple fall events appear in the frame at the same time, HUSKYLENS 2 can mark all fall events with bounding boxes simultaneously, and assign the unified ID 'ID1'.

3.Fall Detection Parameter Settings

The factory default settings of HUSKYLENS 2 already meet basic usage requirements. You can manually adjust each parameter for personalized functions.

All parameters below are based on the Fall Detection function. Therefore, first make sure you have entered the Fall Detection mode as shown in the figure.

To modify a parameter, you can select it by swiping left or right on the parameter text at the bottom of the screen.

3.1 Detection Threshold

Detection Threshold controls the sensitivity of fall detection. The lower the threshold, the looser the detection criteria; the higher the threshold, the higher the confidence score required (stricter judgment). Setting steps: Tap "Detection Threshold". A parameter slider will appear above it. Slide left to decrease the value, slide right to increase it, as shown in the figure.

3.2 NMS Threshold

NMS Threshold is a common parameter in visual recognition used to filter detection boxes. In visual recognition tasks, the model often predicts multiple overlapping detection boxes around the same target. Without filtering, one object may be enclosed by multiple overlapping boxes.

You can adjust the NMS threshold to remove duplicate overlapping boxes and retain only the optimal one. Simply put, the NMS threshold determines how much overlap between two boxes counts as “duplicate”.

For example: - If the threshold is low (e.g., 0.3), two slightly overlapping boxes will be considered duplicates, and one will be removed. - If the threshold is high (e.g., 0.7), two boxes must overlap significantly to be regarded as duplicates, so more boxes may be kept.

Setting steps: Tap “NMS Threshold”. A parameter slider will appear above it. Slide left to decrease the value, slide right to increase it.

3.3 Reset Default

This parameter restores all settings to their default state and clears learned IDs and names, but does not delete exported models (see below for model export details).

Setting steps: Tap "Restore Defaults". When the "Restore default configuration" pop-up appears, tap "OK".

3.4 Export Model

This parameter allows you to save and export the current parameters, learned IDs, and custom names to the local memory of HUSKYLENS 2. It is suitable for scenarios such as migrating parameters to another HUSKYLENS 2 device. No TF card is required for this operation.

Export steps: Tap Export Model. When the “Save configuration to” pop-up (left image) appears, slide the number up or down to select which model slot to save to (up to 5 models can be stored). Then tap the OK button at the bottom-left of the pop-up to confirm. The export will start automatically after confirmation.

View Exported Model: After the “Exporting” pop-up disappears, you can view the exported model files on a computer.

First, connect HUSKYLENS 2 to a USB port on your computer.

Next, use a computer to access the internal memory of HUSKYLENS 2 via the path shown in the figure below.

You will find two model-related files with the extensions .json and .bin.

The number before the file extension is the model number you selected when saving the configuration. Both files can be copied and pasted to other locations.

3.5 Import Model

This parameter allows you to import the model exported from one HUSKYLENS 2 (hereafter referred to as "Husky A") to another HUSKYLENS 2 (hereafter referred to as "Husky B").

This way, Husky B can directly recognize the objects learned by Husky A and display their IDs and names without additional training.

Import steps:

Step 1: Connect Husky A to a computer, then copy the two exported files to the desktop.

Step 2: Connect Husky B to a computer, then paste the two files into the specified folder of Husky B, as shown in the figure. (If the falldown-detection folder cannot be found, please perform 。

Step 3 :The folder will be created automatically after one model import, then return to Step 2.

Step 4: First, make sure you have entered the Fall Detection function. Then tap Import Model. In the "Load configuration" pop-up, slide the number up or down to select the model number to load, which must match the one you saved earlier.

For example, if the model file you pasted into Husky B is config0.json, select the number 0. Finally, tap OK to import. The import is complete when the "Loading" pop-up disappears.

You can then perform a fall detection test.