«Events» Section#
The Events section is intended for displaying vehicle detection events and recognition of vehicle and LP attributes.
The general view of the Events section (Figure 10).
The section is used to display all events of incoming images of the video stream. Receiving and displaying events is performed with minimal delays in a mode close to real time.
By default, the last 10 events are displayed on the page; to view previous events, you need to go to other pages. The pages are navigated using the pagination buttons at the bottom of the page (Figure 11).
When you navigate through the pages of events, the display of new events in the table stops. This is necessary so that the rows in the table do not «move» while viewing the event table. As soon as the user returns to the first page, all new events are loaded automatically.
The number of events on the page is changed using the pagination buttons.
By default, filters are disabled and all new events are automatically loaded into the table.
Description of the content of the event table is given in Table 3.
Table 3. Event table
| Name | Description |
|---|---|
| ID | Event ID |
| Camera | The name of the camera that recorded the event |
| Date | Date and time of event registration |
| Scenario | Scenario of the event registration |
| Event type | The type of the recorded event is set using the scenario |
| Information | |
| Vehicle crop | Crop of vehicle used to recognize attributes |
| Vehicle type | Vehicle attribute showing what type of vehicle |
| Brand | Vehicle attribute showing the recognized vehicle brand |
| Model | Vehicle attribute showing the recognized vehicle model |
| Emergency services | Attribute of belonging of the vehicle to emergency services |
| LP crop | Crop of LP used to recognize the attributes |
| LP symbols | LP attribute providing information about LP symbols |
| Country of registration | LP attribute indicating country of vehicle registration |
| Pedestrian crop | Crop of pedestrian (relevant for pedestrian detection scenarios) |
| Animal crop | Crop of animal (relevant for animal detection scenarios) |
| Monitoring region frame | Monitor region frame showing the monitoring region for vehicle counts or smoke and fire detection |
| Vehicle count | Attribute showing the vehicle count in the monitoring region |
| Fire type | Attribute showing information about the type of fire detected in the monitoring region. Possible values are displayed by detection priority: Fire > Black Smoke > White Smoke > No Fire. |
The numbers for each attribute are an estimation of recognition. The score is defined in the range from 0 to 1, the closer the value is to 1, the more accurate the attribute recognition result is.
Event Card#
The event card shows extended information about the event. To access the event card, click on the event ID (Figure 12).
The event card is a pop-up window (Figure 13).
The description of the information on the event card is given in Table 4.
Table 4. Event card description
| Section | Name | Description |
|---|---|---|
| General | ID | Event ID |
| Camera | The name of the camera that recorded the event | |
| Date | Date and time of event registration | |
| Scenario | Scenario of the event registration | |
| Scenario type | The type of the recorded event is set using the scenario. | |
| Incident type | The type of the detected object. | |
| Handler | The name of the scenario handler. | |
| Track ID | Track ID on which the event was recorded | |
| Frame ID | Frame ID with vehicle image | |
| Comment | A link that opens a comment entry window when clicked. After adding a comment, the link changes to the text of the comment | |
| Frame | Track frames | Vehicle images in original (maximum) resolution: |
| - Track start frame – the last frame on which the tracking of the vehicle ended. | ||
| - Track end frame – the first frame on which the vehicle was detected. | ||
| - Bestshot – frame with a best shot of the track. | ||
| Crops | Vehicle and LP images used for attribute recognition. | |
| Additional information | Type | Vehicle attribute showing the recognized vehicle type |
| Brand | Vehicle attribute showing the recognized vehicle brand | |
| Model | Vehicle attribute showing the recognized vehicle model | |
| Emergency services | Attribute of belonging of the vehicle to emergency services | |
| Color | Vehicle attribute showing the recognized vehicle color | |
| LP symbols | LP attribute providing information about LP symbols. | |
| LP country | LP attribute indicating country of vehicle registration. | |
| Number of axles | Vehicle attribute showing the recognized number of vehicle axles | |
| Public transport | Attribute of belonging of the vehicle to public transport. | |
| Special transport | Attribute of belonging of the vehicle to special transport. | |
| Number of vehicles | Attribute showing the number of vehicles in the selected zone. Available only when working with the «Vehicle counting» handler | |
| Fire types (Fire, Black Smoke, White Smoke, No Fire) | Attributes showing the types of fires detected and the number of zones with detections of the specified type. Available only when working with the «Smoke and Fire Detection» handler |
The numbers for each attribute are an estimation of recognition. The score is defined in the range from 0 to 1, the closer the value is to 1, the more accurate the attribute recognition result is.
Clicking on any frame opens extended frame information. For Track Frames, a pop-up window appears (Figure 14) containing:
- Frame ID – frame identifier.
- Time – date and time of event detection.
- Type – frame type.
- Label – name of the frame type.
- A frame with an object. The frame shows a BBox on the detected vehicle.
For Crops frames, a pop-up window appears (Figure 15) containing:
- Time – date and time of event detection.
- Type – frame type.
- Label – name of the frame type.
- A frame with an object.
Event Filter#
CARS Analytics UI allows you to filter events to limit the display of events on the screen (Figure 16).
The filters are located on the right side of the page and are open by default. Filters can be hidden by clicking on 
.
With the help of filters, the user can quickly find an event. By default, filters are disabled and all new events are automatically loaded into the table.
Events can be filtered by one or more parameters.
All filters except Date, Event IDs, Number of Axles, LP Symbols, Search by image and Autocomplete filters by image support multiple selection. To cancel the filter selection, click on 
.
Filters Scenario, Event Type, Cameras, Emergency Services, Brands, Models, Types, LP Countries and Colors are presented as drop-down lists, these filters support keyboard input to search for titles in the list. The number of objects in the list will change dynamically as characters are entered.
Accuracy settings are available for all filters except Date, Scenario, Event Type, Camera, Event IDs and Lists. To adjust this value, click on 
icon placed on the right of the filter field.
All filters, except for Date, Number of Axles and LP Symbols, can be configured to filter by the selected value, or by excluding the selected value. By default, all filters have an icon 
next to the field, which means that the filter will be executed according to the selected value. When clicked, the icon will change to 
. In this case, the filter will be executed with the exception of the selected value, that is, for all values except those specified in the field.
The description of each filter is presented in Table 5.
Table 5. Filters description
| Filter | Description | Values |
|---|---|---|
| General | ||
| Date from | Time range of event registrations. It is set using the built-in calendar. | DD.MM.YYYY HH.MM |
| Date to | Time range of event registrations. It is set using the built-in calendar. | DD.MM.YYYY HH.MM |
| Scenario | Dropdown list containing event scenarios. | Scenarios created by the administrator (see section 5). |
| Event Type | A dropdown list containing event types. | Animal – animal detection; |
| Human – pedestrian detection; | ||
| Transport – vehicle detection. | ||
| Camera | Drop-down list of cameras connected in the Cameras section. | Cameras connected by the administrator. |
| Event ID | Field for entering event ID | ID of any created event (e.g. e96af9df-32d5-40a6-b5cf-32e9c04632f8) |
| Lists | Drop-down of lists, added in Lists sections | Lists added by Administrator (see section 6) |
| Accuracy | The field for specifying the accuracy value of the vehicle and LP attributes. Accuracy is set for the following fields: Emergency services, Special transport, Public transport, Number of axles, Brands, Models, Vehicle types, Vehicle colors, LP symbols, LP Country. The sample includes values whose determination accuracy is equal to or higher than the entered one. The accuracy value is entered in the range from 0 to 1. Entering values less than 0 or greater than 1 will result in an error. It is not recommended to enter more than three decimal places. | 0.000…1.000 |
| Vehicle | ||
| Search by images | Search for a vehicle or LP by a given image. The search process is described in section 3.3. | Vehicle image |
| Autocomplete filters by image | Uploading a vehicle image for autofill filters and searching for these filters. The process of using autofill is described in Section 3.4 | Vehicle image |
| Emergency services | Drop-down list with the type of emergency services. | - (-) Non-emergency - civil vehicles, military, etc. |
| - Fire brigade - vehicle of the fire service. | ||
| - Police - TC police and traffic police. | ||
| - Ambulance - ambulance vehicles. | ||
| - Gas Service – vehicles of gas service. | ||
| - (112) MES – vehicles of rescue services. | ||
| Special transport | Drop-down list with the type of special transport. | - forklift, |
| - sweeper, | ||
| - paver | ||
| - concrete mixer, | ||
| - bulldozer, | ||
| - grader, | ||
| - truck, | ||
| - roller, | ||
| - garbage truck, | ||
| - sprinkler truck, | ||
| - other special, | ||
| - dump truck, | ||
| - tractor, | ||
| - excavator, | ||
| - other, | ||
| - non-special | ||
| Public transport | Drop-down list with the type of public transport. | - carsharing, |
| - public transport, | ||
| - other, | ||
| - taxi, | ||
| - not defined | ||
| Number of axles | Input field for the number of vehicle axles. | 2…12 |
| Brands | Drop-down list with vehicle brands | Brand available in the drop-down list |
| Models | Drop-down list with vehicle brands | Models available in the drop-down list. |
| Types | Drop-down list with vehicle types: | - А_light, |
| - А_heavy, | ||
| - В_light, | ||
| - B_heavy, | ||
| - С_light, | ||
| - С_heavy, | ||
| - D_light, | ||
| - D_heavy, | ||
| - D_long, | ||
| - E_light, | ||
| - E_heavy, | ||
| - P_light, | ||
| - P_heavy, | ||
| - Other, | ||
| - Undefined | ||
| See the description of each type in CARS API Administration manual | ||
| Colors | Drop-down list of vehicle colors. | - beige, |
| - black, | ||
| - blue, | ||
| - brown, | ||
| - cherry, | ||
| - golden, | ||
| - gray, | ||
| - green, | ||
| - light_blue, | ||
| - orange, | ||
| - pink, | ||
| - red, | ||
| - silver, | ||
| - violet, | ||
| - white, | ||
| - yellow | ||
| LP Symbols | ||
| LP Symbols | The field for entering LP symbols. Unknown characters must be replaced with *. LP length should be from 7 to 9 characters. Examples of LP: A001AA777, A*A777, A000177, etc. When entering a different number of characters, an error appears informing about the wrong number of characters and this filter will not be used for filtering. |
Numbers 0…9, Capital letters A…Z |
| LP Country | Drop-down list of countries of vehicle registration. | Values available in the drop-down list. |
The User needs to set one filter or a combination of them and click the «Apply» button for the settings to be applied.
The list of supported vehicle brands and models depends on the selected version of the classifier for recognition (for more information, see "LUNA CARS API. Administration Manual"). If the classifier of the latest version is selected, more than 160 models and 1700 brands are supported in the system.
The recognition of the make and model of the vehicle in the system is performed by the appearance of the vehicle body.
Vehicles of different brands and models, but having a similar body type, the system refers to the same brand and model – the most common in the Russian Federation. For example, ZAZ Sens, ZAZ Lanos, ZAZ Chance, Daewoo Sens, Daewoo Lanos, Chevrolet Lanos, ZAZ Lanos Furgon have a similar appearance, and LUNA CARS defines these models as Chevrolet Lanos. At the same time, by setting the "Daewoo" brand and the "Sens" model in the filters, the filtering results will include events with any vehicle of the above brands and models (i.e., any of these models can be on the vehicle image), but "Chevrolet" and "Lanos" will be displayed in the "Brand" and "Model" fields, respectively.
A complete list of related brands and models is presented in the "LUNA CARS API. Administration Manual".
The icon 
to the left of the "Filters" header, clicking opens the report generation settings window. All events corresponding to the set filters, taking into account the settings, will be included in the report. The report is created as part of a background task. Working with tasks is described in Section 9.
To reset the entered values, click the "Reset" button or next to the filters icon to the right of the "Filters" header.
Search by Image#
CARS Analytics UI supports search by vehicle image (Figure 17). The result of the search by image is a list with all events whose descriptor matches the descriptor of the loaded image with a given accuracy. The image of the vehicle must meet the requirements (Table 6).
Table 6. Image requirements
| Parameter | Requirements |
|---|---|
| Resolution | from 100x100 px to 1920х1080 px |
| Maximum file size | 3 Mb |
| Image color | Color or black and white image |
| Image Format | JPG or PNG |
| Frame composition | - Vehicle and LP must be fully visible (not blocked by other objects); |
| - Image should not contain more than one vehicle |
After clicking on the 
, the window for adding a file will open (Figure 18).
To add an image, click on the appropriate space and select a file from the explorer, or drag the necessary file into the space.
After adding the image, the system will prompt you to set the accuracy value for recognition. Accuracy can be removed by clicking on the "Remove accuracy" link (Figure 19).
To reset the image, click 
in the upper left corner of the image.
When a supported image is selected, the icon of this feature will change its color to blue and the «Filter» button will change to «Create task» (Figure 20).
When you click on the «Create task» button, a background task for searching by image is generated.
The search result is presented in the Tasks section (see Section 9).
Autocomplete filters by image#
CARS Analytics UI supports auto-completion of filters by vehicle image (Figure 21).
After clicking 
the window for file upload will open (Figure 22).
To add an image, click on the label "Click or drag a file" and select a file from the explorer, or drag the desired file into the file addition window. The uploaded vehicle image must meet the requirements specified in Table 6 (see section 3.3).
The result of image processing is the recognized attributes of the vehicle and LP, which can be used to search for events. Recognizable attributes to fill in:
- Brand;
- Model;
- Country;
- LP;
- General transport;
- Special transport;
- Color;
- Emergency services;
- Type.
Each attribute can be selected/removed from the selection for use in filters by clicking on the checkbox next to the attribute.
In order to reset the image, you need to click on in the upper left corner of the image.
After clicking the "Apply" button (Figure 23), the filters will be automatically filled in and applied according to the values of the recognized attributes.
