1.About DeepSight Toolkit
About DeepSight Toolkit
DeepSight Toolkit is a simple cross-platform plug & play solution that enables you to detect and analyze multiple faces using just one application!
Get insights into your audience demographics and viewer behaviour and optimize messaging in real-time with no need for hard coding. The software can be installed with ease by anyone within minutes!
- Age Estimation
- Gender Estimation
- ID Detection
- Head Position/Head Gaze
- Attention Time
- Analyzed features: age, gender, smile, head pose, attention and more!
- Easy and quick setup: the software can be installed with ease by anyone within minutes.
- CMS Integration: using http request in JSON format.
- Real-time results: no need to wait for data to be displayed.
- Anonymous analysis: no video is ever recorded and no identifiable facial features are stored.
- Cross-Platform: Toolkit runs on Windows and Linux (Android coming soon!).
- Processed Locally: all data is analyzed on the device.
- Push mechanism: send messages from Toolkit to multiple external applications.
- Works with most cameras: from budget USB cameras to high definition IP cameras.
- No internet needed: analysis runs offline (one-time authentication).
1.3.Quick installation guide
Preparations for installation:
Step 1. Make sure your device has Internet connection for license authentication (by browsing google.com, for example).
Step 2. Make sure the web/inbuilt camera on your device is installed and is running as expected (by opening camera app, for example).
Download the DeepSight Toolkit for your preferred operating system.
For Windows device, please allow the app to make changes to your device and run it.
Follow the setup instructions and accept the licensing agreement to continue.
You can now access your application folder and double click to activate and initialize the Toolkit.
After the Toolkit is installed, you will need to enter a valid license.
Go to the “Licensing” tab to add your license key.
You are now ready to start using the DeepSight Toolkit.
2.Using the Toolkit
A CSV file is a comma separated values file which allows data to be saved in a table structured format. The Toolkit generates two CSV files: one containing raw data gathered during the real-time analysis, and another with pre-aggregated data for each person ID. The raw data can be used for post-processing.
To enable CSV exports go to the Output tab and make sure the checkbox Save data to CSV is checked. By default, the CSV files will be automatically generated in the Toolkit configuration folder after each analysis. Users can also specify the location where the CSV files will be stored. Every row in the raw data CSV file contains the analysis for 1 frame. In the aggregated CSV file each row contains data for one individual ID/person.
The first row of the CSV file contains the label of the respective column.
The HTTP interface can be used to connect any Business Intelligence platform or CMS to the Toolkit. Go to ‘Output’ Tab and click on the fields: ‘Enable Pull’. You have the option to either get raw or aggregated data.
The JSON response can be accessed through a GET request on localhost for your external application. You can use this function for instance for Digital Signage or narrowcasting applications which trigger custom and relevant ad content to the right people at the right time.
For the raw data JSON output you can access: http://localhost:8080/JSON
For the aggregated JSON output you can access: http://localhost:8080/JSONAGGR
The push mechanism allows for messages to be sent from the Toolkit to external applications (eg. CMS systems) instead of requiring the external application to actively ask the Toolkit for changing status (pulling). Therefore the Toolkit can push data into any external application or API.
If the push feature is enabled, the Toolkit will send an HTTP POST request to the endpoint defined by the user every second. The endpoint needs to be a valid HTTP server able to receive HTTP POST requests. The body of the HTTP POST request is a JSON object containing a summary of the last second of analysis. You can add the target URL directly in the Toolkit interface.
It might be desirable to start the Toolkit on startup of the system. For both platforms it is required that you log in automatically when the system is turned on, eg. you are not required to enter a password and you’re instantly booted to the Desktop.
In the installation directory of the Toolkit there is a default start.bat script that can be used and modified for automatic startup of the Toolkit from the command line. Once the start.bat script has been modified in accordance to your preference, you can use this script for automatically starting up the Toolkit as follows:
1. Use the Windows key + R keyboard shortcut to open the Run command
2. Type shell:startup to open the Startup folder of Windows. All shortcuts placed in this directory will be called when Windows has started
3. Right-click and select New > Shortcut
4. Browse and select the start.bat file
5. Double-check if the Toolkit starts up when you double-click the shortcut
6. If the Toolkit launches in step 5, you’re all set for automatic startup
Although our DeepSight Toolkit is hardware and camera agnostic, this section gives a few recommendations for devices that you can use in different scenarios. In case none of these machines match your requirements, you are free to choose your own device according to the following general specifications;
Intel® Core™ i3-10110U (4M Cache, up to 4.10 GHz)
NUC 10th generation
RAM: 8 GB
Storage at least 2 GB free space
Intel® Core™ i5-10210U (6M Cache, up to 4.20 GHz)
NUC 10th generation
RAM: 8 GB
Storage at least 2 GB free space
(Please note that hardware type significantly influences the software performance therefore choose your devices carefully)
Recommended Intel NUCs:
Not sure which Passmark applies to your device? Check it here.
There are many different camera types on the market that work with the Toolkit, but to make your decision making easier below we list a few preferred models per industry that we and our clients use frequently;
AXIS F Series cameras
1. “Couldn’t resolve host name”
The Toolkit is trying to authenticate the license key against our licensing server but there is no internet connection available. Try connecting to network first and then running the software again. After the initial authentication, the software runs offline so there is no need for active internet connection.
2. “Cannot initialize log rotation”
This error occur due to the fact that Toolkit does not have permissions to write log files in the specified directory. To fix this you can either start the Toolkit as administrator or set the log folder where the Toolkit has permissions (eg: a folder in the Desktop). If the logs files cannot be generated, the Toolkit will still be working.
Please refer to our help desk.
Please contact us for further resources.