You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: metro-ai-suite/sensor-fusion-for-traffic-management/deployments/how_to_generate_kitti_format_dataset/requirements.txt
Copy file name to clipboardExpand all lines: metro-ai-suite/sensor-fusion-for-traffic-management/deployments/how_to_support_yolov6_model/requirements.txt
The **Smart Traffic Intersection Agent (STIA)** provides comprehensive traffic analysis capabilities including real-time intersection monitoring, directional traffic density analysis, and VLM-powered traffic insights. This guide provides step-by-step instructions to:
3
+
The **Smart Traffic Intersection Agent (STIA)** provides analytics that include, but not limited to, real-time intersection, directional traffic density, and VLM-powered traffic. This section shows you how to:
4
4
5
5
- Set up the agent using the automated setup script for quick deployment.
6
-
- Run predefined tasks to explore its functionality.
7
-
-Learn how to modify configurations to suit specific requirements.
6
+
- Run predefined tasks to explore the agent's functionality.
7
+
-Edit configurations to suit specific requirements.
8
8
9
9
## Prerequisites
10
10
11
11
Before you begin, ensure the following:
12
12
13
-
-**System Requirements**: Verify that your system meets the [minimum requirements](./system-requirements.md).
14
-
-**Docker Installed**: Install Docker. For installation instructions, see [Get Docker](https://docs.docker.com/get-docker/).
15
-
-**MQTT Broker**: Ensure access to an MQTT broker for traffic data streaming (or use the included broker).
16
-
17
-
This guide assumes basic familiarity with Docker commands and terminal usage. If you are new to Docker, see [Docker Documentation](https://docs.docker.com/) for an introduction.
13
+
-**System requirements**: Verify that your system meets the [minimum requirements](./system-requirements.md).
14
+
-**Docker platform**: Install Docker platform. For installation instructions, see [Get Docker](https://docs.docker.com/get-docker/).
15
+
-**Message Queuing Telemetry Transport (MQTT) Broker**: Ensure access to an MQTT broker for traffic data streaming, or use the included broker.
16
+
-**Docker commands and terminal usage**: You are familiar with Docker commands and using the terminal. If you are new to Docker, see [Docker Documentation](https://docs.docker.com/) for an introduction.
18
17
19
18
## Quick Start with Setup Script
20
19
21
-
The Smart Traffic Intersection Agent includes an automated setup script that handles environment configuration, submodule and dependencies setup, secrets generation, building, and deployment. This is the **recommended approach** for getting started.
20
+
Intel recommends using the automated setup script that handles environment configuration, submodule and dependencies setup, secrets generation, building, and deployment of the Smart Traffic Intersection Agent.
22
21
23
22
### 1. Clone the Repository
24
23
@@ -29,42 +28,44 @@ cd metro-ai-suite/smart-traffic-intersection-agent/
29
28
30
29
### 2. Run the Complete Setup
31
30
32
-
Easiest way to setup the service is to use the default configurations without making any changes. Run the setup script with --setup option for quick setup of the application with default configuration :
31
+
The easiest way to set up the service is to use default configurations without making any changes. Run the setup script with the --setup option to set up the agent quickly with default configurations:
33
32
34
33
```bash
35
34
source setup.sh --setup
36
35
```
37
36
38
37
This single command will:
39
38
40
-
- Set all required environment variables with default values
41
-
-Setup all dependencies and submodules required for Traffic Intersection Agent
42
-
- Generate required TLS certificates and authentication files
39
+
- Set required environment variables with default values
40
+
-Set up dependencies and submodules required for Smart Traffic Intersection Agent
41
+
- Generate the required TLS certificates and authentication files
43
42
- Download demo video files for testing
44
43
- Build Docker images
45
-
- Start all services in the Traffic Intersection Agent application stack
44
+
- Start services in the Smart Traffic Intersection Agent's application stack
46
45
47
46
### 3. Access Services
48
47
49
-
Once the script is completed successfully, it will show the URLs to access the services. Head to these URLs for the respective services to access them in a web browser.
48
+
When the script completes, it will show the URLs to access the services. Go to these URLs so that the respective services can access them in a web browser.
49
+
50
+
## Running Multiple Instances (Test or Development Only)
50
51
51
-
## Running Multiple Instances (Test/Dev Only)
52
+
For testing or development purposes, you can run multiple instances of the Smart Traffic Intersection Agent to simulate multiple intersections on the same development machine or node. The easiest way to do this is to clone and set up the application `n times` in n different locations on the same machine for `n` required instances.
52
53
53
-
For testing or development purposes, you might want to run multiple instances of the Smart Traffic Intersection Agent to simulate multiple intersections on the same development machine/node. Easiest way to do this is to clone and setup the application `n times` in n different locations on the same machine for `n` required instances. Please note that in production environments, only a single Traffic Intersection Agent instance is deployed on a given node.
54
+
> **Note**: In production environments, only a single Traffic Intersection Agent instance is deployed on a given node.
54
55
55
-
> **Recommendation**: The number of instances you can run on a single machine, depends on available resources. Systems with higher resources can support more instances.
56
+
> **Intel's recommendation**: The number of instances you can run on a single machine depends on available resources. Systems with higher resources can support more instances.
56
57
57
-
### Setting up Instance #1
58
+
### Set up Instance #1
58
59
59
-
#### 1. Clone the repository into a new directory:
cd edge-ai-suites-instance2/metro-ai-suite/smart-traffic-intersection-agent/
100
101
```
101
102
102
-
#### 2. Edit deployment config for Instance#2
103
+
2. Edit the deployment configuration for instance#2:
103
104
104
105
```bash
105
106
nano src/config/deployment_instance.json
106
107
```
107
108
108
-
Following is a sample value for the Instance #2 deployment config:
109
+
The following is a sample value for instance #2 deployment configuration:
109
110
110
111
```json
111
112
{
@@ -116,30 +117,30 @@ Following is a sample value for the Instance #2 deployment config:
116
117
"agent_ui_port": "7861"
117
118
}
118
119
```
119
-
#### 3. Run Setup for Instance #2
120
+
3. Run Setup for Instance #2
120
121
121
122
```bash
122
123
source setup.sh --setup
123
124
```
124
125
125
-
> __**NOTE**__: Keep `agent_backend_port` and `agent_ui_port` values empty to use random ephemeral ports and avoid port conflicts.
126
+
> **Note**: Keep the`agent_backend_port` and `agent_ui_port` values empty to use random ephemeral ports and avoid port conflicts.
126
127
127
128
128
129
Ensure each instance has their `deployment_instance.json` updated with:
129
130
- A unique value for `name` field
130
131
- Unique latitude and longitude co-ordinates
131
-
- Different `agent_backend_port` and `agent_ui_port` values to avoid port conflicts (optional — if not specified, an ephemeral port is picked automatically)
132
+
- Different `agent_backend_port` and `agent_ui_port` values to avoid port conflicts. This is optional. If not specified, an ephemeral port is picked automatically.
132
133
133
-
### Deploying more instances
134
+
### Deploying More Instances
134
135
135
-
There are functionally no limits on number of instances which you can spin-up to simulate multi-node setup using the provided script. However, the machine on which the multiple deployment is being done, will likely start throttling these instances if resource limits are reached. Hence, deploy new instances only if you have the required resource bandwidth.
136
+
There are functionally no limits on the number of instances that you can spinup to simulate a multi-node setup using the provided script. However, the machine on which the multiple deployments are deployed to, will likely start throttling these instances if resource limits are reached. Hence, deploy new instances only if you have the required resource bandwidth.
136
137
137
-
To spin-up more instances - say `n number of new instances`, repeat the steps mentioned to[Setting up Instance #2](#setting-up-instance-2), by changing to a new directory `n` times.
138
+
To spin-up more instances - say `n number of new instances`, repeat the steps mentioned in[Setting up Instance #2](#setting-up-instance-2), by changing to a new directory `n` times.
138
139
139
140
140
141
## Advanced Environment Configuration
141
142
142
-
For advanced users who need more control over the configuration, following environment variables can be configured before running the setup script to override the default behaviour.
143
+
For advanced users who need more control over the configuration, you can configure the following environment variables before running the setup script to override the default behaviour:
143
144
144
145
```bash
145
146
# Set log level to debug to help in debugging issues, default value is info
@@ -163,9 +164,9 @@ export TRAFFIC_BUFFER_DURATION=20 # Default value 30; Analysis window of tr
163
164
164
165
## Accessing the Services
165
166
166
-
As the setup process, as mentioned above, completes successfully, the URLs for all services are displayed on the terminal. We can get the URL for **Traffic Intersection Agent UI** and **Traffic Intersection Agent API Docs** from the response and access it in a web browser.
167
+
After the setup processcompletes, the URLs for all services are displayed on the terminal. You can get the URL for **Traffic Intersection Agent UI** and **Traffic Intersection Agent API Docs** from the response, and access it in a web browser.
167
168
168
-
Following is a sample response you might get at the completion of script, which displays all the URLs to access the relevant services:
169
+
The following is a sample response that you might get at script completion, which displays the URLs for accessing the relevant services:
169
170
170
171
171
172
@@ -174,7 +175,7 @@ Following is a sample response you might get at the completion of script, which
174
175
175
176
### Port Conflicts for Traffic Intersection Agent Backend or UI
176
177
177
-
Please make sure the the config file at `src/config/deployment_instance.json` for all instances (deployed from different directories, in case of multiple deployment on same machine) has empty values for following fields `agent_backend_port`, `agent_ui_port`as follows:
178
+
Ensure that the config file at `src/config/deployment_instance.json` for all instances (deployed from different directories, in case of multiple deployment on same machine) has empty values for the `agent_backend_port` and `agent_ui_port`fields:
178
179
179
180
```bash
180
181
...
@@ -183,5 +184,5 @@ Please make sure the the config file at `src/config/deployment_instance.json` fo
183
184
...
184
185
```
185
186
186
-
It is recommended to keep these values empty and let Docker use ephemeral ports for minimal hassle. However, if it is required to provide a explicit port, then make sure all such port values for all instances are unique. Also, make sure no other external services are running on these ports.
187
+
Intel recommends to keep these values empty and let the Docker engine use ephemeral ports for minimal hassle. However, if you need to provide an explicit port, ensure port values for all instances are unique. Also, ensure no other external services are running on these ports.
Copy file name to clipboardExpand all lines: metro-ai-suite/smart-traffic-intersection-agent/docs/user-guide/how-it-works.md
+6-6Lines changed: 6 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,11 +1,11 @@
1
-
# How to Build from Source
1
+
# How It Works
2
2
3
-
Build the Scene Intelligence microservice from source to customize or extend its functionality. This guide covers building the containerized Traffic Intersection Agent.
3
+
This section shows how to build the Smart Traffic Intersection Agent from source to customize or extend its functionality.
4
4
5
5
## Prerequisites
6
6
7
-
-**System Requirements**: Verify your system meets the [minimum requirements](./system-requirements.md).
8
-
-**Docker**: Install Docker from [Get Docker](https://docs.docker.com/get-docker/).
7
+
-**System Requirements**: Verify that your system meets the [minimum requirements](./system-requirements.md).
8
+
-**Docker platform**: Install Docker platform from [Get Docker](https://docs.docker.com/get-docker/).
This page provides detailed hardware, software, and platform requirements to help you set up and run the microservice efficiently.
3
+
This section shows the hardware, software, and platform requirements to help you set up and run Smart Traffic Intersection Agent efficiently.
4
4
5
-
## Supported Platforms
5
+
The agent currently supports CPU- and GPU-based runs, and runs in the context of video summary pipeline. Hence, the system requirements is as per the documentation in the sample application.
6
6
7
-
This microservice currently supports CPU and GPU based runs. This microservice is intended to run in the context of video summary pipeline. Hence, supported platform, OS configuration etc. is as per the documentation in the sample application. The documentation here, hence, does not provide separate requirements.
0 commit comments