Configuring VIDIZMO Vision Indexer for Object Detection
Overview
The VIDIZMO Vision Indexer uses AI to process videos, images, and documents, extracting insights such as detected objects and recognized characters. These insights improve content categorization, indexing, and search, making it easier to find relevant results in your portal.
You can configure the Vision Indexer to automatically process AI insights and apply settings that match your workflow. Options include automatic redaction of selected insights and control over how processed output files are handled. Automating these tasks reduces manual effort and speeds up content processing while ensuring consistent results.
Pre-requisites
To configure the VIDIZMO Vision Indexer, ensure:
- You are part of a group with feature permissions to configure the VIDIZMO Vision Indexer.
- You have specific feature permissions for each detection type you intend to configure. For example, to configure Face Detection settings, your group must have permissions enabled explicitly for the face detection feature.
For details about managing groups and enabling feature permissions, see Enable Features in the VIDIZMO Portal.
Accessing the Configuration
Follow these steps to access the VIDIZMO Vision Indexer configuration screen.
Navigate to Portal Settings
- Click on the menu icon on the top left-hand corner of the screen to bring up the left navigation pane.
- Click the down arrow to expand the Admin section.
- Select Portal Settings.
Access Content Processing Apps
- Navigate to Portal Settings and click on Apps in the navigation pane to expand the list of application types available in VIDIZMO.
- Select Content Processing, where you can set up VIDIZMO Vision Indexer.
- Access the configuration options by clicking the VIDIZMO Vision Indexer's settings icon.
Object Detection Configuration
This section describes the settings available for configuring object detection in the VIDIZMO Vision Indexer.
Supported Media/Evidence Types
Select the available Media or Evidence type. Choose from the following:
- Image
- Video
- Document
Note: VIDIZMO also supports images with equirectangular projection (such as panoramic images) for object detection.
The configuration screen of the VIDIZMO Vision Indexer is designed to show the dependency of each field according to the selected Media/Evidence and detection type(s).
Detection Types
Select the required detection method: Object Detection, OCR, or both, depending on your use case.
- Object Detection: Detects visual objects in content
- OCR: Optical Character Recognition for text extraction
Supported Object Detection Classes
The VIDIZMO Vision Indexer can detect the following object classes:
Person
Gun
Knife
Train
Car
Bus
Truck
Boat
Bike
Airplane
License Plate
Screen
Laptop
Display
Cellphone
Signature
Street Sign
Head
Eyes Protection
No Eyes Protection
Nose Mouth Protection
No Nose Mouth Protection
Head Protection
No Head Protection
Hand Protection
No Hand Protection
Foot Protection
No Foot Protection
Safety Vest
No Safety Vest
House Number
Pothole
Fallen Tree
Graffiti
Fire Extinguisher
Bulletproof Vest
Mailbox
When you select one or more Object Detection Classes, a configuration field appears for each selected class. These fields allow you to define detection behavior individually for each object type.
Confidence Threshold
Specifies the minimum confidence score required for an object to be detected.
Range: 10–99 Default: 45
Effect: Higher values increase precision but may reduce the number of detected instances, while lower values increase sensitivity.
For each selected class, you can configure the confidence threshold setting.
Face Detection Settings
When Face Detection is selected in the VIDIZMO Vision Indexer, additional configuration options become available to refine how facial analysis is performed.
Facial Attributes: Choose the facial attribute you want to detect from the options:
- Age
- Gender
- Race
Note: The selected facial attributes are detected when a video or image undergoes the Face Detection activity. After processing, the selected facial attributes are displayed on the processed file's playback page.
Video Processing Settings
The following settings apply specifically to video content processing.
Tracking Frame
Specifies the number of consecutive frames in which an object must be detected before it is considered valid.
Range: 3–30
Effect: The model will only consider those objects that appear in the specified number of consecutive frames and disregard those that don't meet this threshold.
Note: This setting applies only to videos.
Frame Forward Count
Controls the stride of video analysis for visual objects (for example, Street Sign, Face, Person). After VIDIZMO processes one video frame, it moves forward by this many frames before processing the next one.
Range: 1–15
Effect:
- Lower values analyze frames more frequently (higher accuracy, less flicker).
- Higher values skip more frames (faster processing, but can miss brief objects).
- Lower values help reduce redaction flicker by increasing continuity between analyzed frames.
When to adjust:
- Decrease (1–3): For fast motion, quick object appearances, or redaction-critical workflows.
- Increase (4–10): For stable footage when you need faster throughput and objects persist on screen.
OCR Frame Forward Count
Controls the stride for OCR (text or character) analysis in videos. After VIDIZMO completes OCR on one frame, it moves forward by this many frames before running OCR again.
Range: 1–30
Effect:
- Similar to frame forward count, lower values capture transient or small text more reliably.
- Higher values speed up OCR on long recordings but may miss fleeting text.
- Improves OCR detection stability on moving footage.
- Helps reduce redaction flicker when masking text that appears across consecutive frames.
When to adjust:
- Decrease (1–3): For bodycam/dashcam footage, panning cameras, or rapidly changing text.
- Increase (6–15, up to 30 as needed): For static scenes where on-screen text persists.
Note: This field applies only when OCR is selected as the detection type.
OCR Language
The OCR Language field allows you to choose the language for Optical Character Recognition (OCR) during processing. Select from the dropdown menu the language that matches your content for optimal text extraction accuracy.
For more details on OCR processing, refer to: How to Perform OCR using VIDIZMO Vision Indexer
Redaction Settings
The VIDIZMO Vision Indexer includes settings for automatically redacting detected objects within your content.
Note: Redaction settings are only available if you belong to a group with Redaction or Bulk Redaction features enabled.
Automatic Object Redaction
The automatic redactions are applied to detections generated either through the automatic processing of uploaded media or through on-demand processing initiated by the user.
The objects that the Vision Indexer will automatically redact depend entirely on the detection types or AI insights you specify in the redaction settings. This ensures that only the objects you have explicitly enabled for detection will be subject to redaction.
Redaction Type(s)
Select the detection types that you want the indexer to redact automatically during content processing.
Redaction Sub Type(s)
Select specific subtypes for redaction. The available options depend on the Object Detection Classes you previously configured in the Vision Indexer. Only the selected classes will be processed for redaction, ensuring precise and targeted results.
Confidence Threshold for Redaction
Specifies the minimum confidence threshold for automatic redaction.
Range: 25–99
Effect: Objects detected with confidence levels equal to or greater than the threshold you set will be automatically redacted by the VIDIZMO Vision Indexer.
Visual Masking Style
The Visual Masking Style option allows you to choose how objects are redacted in your content. Select the masking style that best suits your needs:
- Solid: Fully blackens out the selections when they are processed for redaction.
- Pixelate: Distorts the content by replacing the selections with a grid of blocks.
- Blur: Obscures the selections by applying a blurring effect, making the objects unclear.
Automatic Document Redaction
Document redaction settings define how documents uploaded to your Portal are processed for automatic redaction activity. This functionality only works on editable documents (which are documents with selectable text) and only becomes available if Document is selected in the Media or Evidence Types.
To redact specific information from documents, the Vision Indexer utilizes Custom Patterns. You can configure the Indexer with the patterns available on your Portal. VIDIZMO provides you with global patterns by default, but you can also create your custom patterns using regex or plain text; see How to Create Custom Patterns for more.
Patterns: Add patterns to redact specific information from documents. During the automatic redaction activity, the VIDIZMO Vision Indexer scans documents for matches to these patterns and automatically redacts that data.
Advanced Processing
The advanced processing options determine how the original file (the file selected for processing) is handled during automatic redaction and how the output is generated.
Note: These settings are only displayed when:
- Any detection type or category is added in the Redaction Type(s)
- Automatic Processing is turned on.
Action for Original File
Select the default action for the original file(s) undergoing the automatic redaction process. The options are:
- Retain File: The Indexer creates a copy of the original file and performs detection and redaction on this copy. The original file remains intact and unmodified.
- Delete and Move to Recycle Bin: The Indexer creates a duplicate for processing as above, but after processing, the original file is deleted and sent to the Recycle Bin.
- Override Original File: The Indexer performs detection and redaction directly on the original file, modifying it by adding metadata or timed data as part of the process. No duplicate is created, so the original file is changed.
To learn more about these settings, refer to the Advanced Processing Options section in Understanding Automatic Redaction via VIDIZMO Vision Indexer
Apply Redaction Codes
Select whether redaction codes are automatically applied during upload.
- On: Redaction codes mapped to detection classes are automatically applied to uploaded files during automatic redaction workflows.
- Off: Redaction codes are not automatically applied to uploaded files.
Note: This setting only affects automatic redaction. Manual redaction and redaction performed in Studio are not impacted by this setting.
Automatic Processing
Choose whether to turn automatic processing on or off. Enable Automatic Processing: Toggle the switch "On" to enable automatic object detection for your uploads. This eliminates the need for manual intervention.
Saving Configuration
Once you have completed the configuration, click the Save Changes button to apply the configured settings.
Enable Vision Indexer
Enable the VIDIZMO Vision Indexer via the toggle button to enable (both automatic and on-demand) processing for object detection or automatic redaction in your Portal.
A notification will appear briefly when the application is enabled, stating "App Settings Updated Successfully."
