Difference between revisions of "Recording Video from Depth Sensor Environment"

From iPi Docs
Jump to: navigation, search
(Created page with "=== Environment === For a single or dual depth sensor configuration, you need a minimum of 10 feet by 10 feet space (3 meters by 3 meters). At smaller space, actor simply won...")
 
m
 
(10 intermediate revisions by 2 users not shown)
Line 1: Line 1:
 
=== Environment ===
 
=== Environment ===
  
−
For a single or dual depth sensor configuration, you need a minimum of 10 feet by 10 feet space (3 meters by 3 meters). At smaller space, actor simply won’t fit into view of cameras.
+
Minimum space requirements for depth sensor configurations depend on sensor model and number of sensors:
  
−
It is convenient to put MS Kinect Sensor on a chair or a table. The picture below will help you to understand possible capture area and required space. Dimensions are different for Kinect and Kinect 2 sensors due to different field of view.
+
{| class="wikitable" border="1"
 +
! Configuration  !! Azure Kinect (WFOV mode) !! Azure Kinect (NFOV mode)<br/>Kinect 2 (Kinect for Xbox One) !! 1st gen. Depth Sensors<br/>Orbbec Astra (Pro)
 +
|-
 +
| Single Depth Sensor ||
 +
7 by 5 feet = 2 by 1.5 meters
 +
||
 +
8 by 5 feet = 2.5 by 1.5 meters
 +
||
 +
10 by 10 feet = 3 by 3 meters
 +
|-
 +
| 2 Depth Sensors<br/>(90-degrees config.) ||
 +
7 by 7 feet = 2 by 2 meters
 +
||
 +
8 by 8 feet = 2.5 by 2.5 meters
 +
||
 +
10 by 10 feet = 3 by 3 meters
 +
|-
 +
| 2 Depth Sensors<br/>(180-degrees config.) ||
 +
12 by 7 feet = 3.5 by 2 meters
 +
||
 +
16 by 8 feet = 5 by 2.5 meters
 +
||
 +
20 by 10 feet = 6 by 3 meters
 +
|-
 +
| 3+ Depth Sensors ||
 +
12 by 12 feet = 3.5 by 3.5 meters
 +
||
 +
16 by 16 feet = 5 by 5 meters
 +
||
 +
20 by 20 feet = 6 by 6 meters
 +
|}
  
−
==== Kinect 2 for Windows and Kinect for Xbox One ====
+
Maximum capture area is about 7 by 7 feet ( = 2 by 2 meters), for all sensor models and configurations.
 +
 
 +
The pictures below will help you to understand possible capture area and required space. Dimensions are different for Azure Kinect, Kinect 2 (Kinect for Xbox One) and 1st gen. depth sensors due to different field of view.
 +
 
 +
==== Azure Kinect in NFOV mode and Kinect 2 for Windows (Kinect for Xbox One) ====
 +
 
 +
Kinect 2 (Kinect for Xbox One) sensors and Azure Kinect sensors in NFOV mode (narrow-view mode) have very close view angles (less than Azure Kinect in WFOV mode, but greater than 1st gen. depth sensors and Orbbec Astra):
  
−
Kinect 2 sensors have wider angle of view compared to first generation Kinect. This makes possible to come closer to sensor thus decreasing overall space requirements.
 
 
<center><table border=0><tr>
 
<center><table border=0><tr>
−
<td>[[Image:K2Sensor-scene-side-view.png|center|385px|Click to enlarge]]</td>
+
<td>[[Image:K2Sensor-scene-side-view.png|center|469px|Click to enlarge]]</td>
−
<td>[[Image:K2Sensor-scene-top-view.png|center|394px|Click to enlarge]]</td>
+
<td width="15"></td>
 +
<td>[[Image:K2Sensor-scene-top-view.png|center|424px|Click to enlarge]]</td>
 
</tr><tr>
 
</tr><tr>
−
<td><center>'''Side view'''</center></td><td><center>'''Top view'''</center></td>
+
<td><center>'''Side view'''</center></td><td></td><td><center>'''Top view'''</center></td>
 
</tr></table></center>
 
</tr></table></center>
  
−
==== First Generation Kinect ====
+
==== Azure Kinect in WFOV mode ====
 +
 
 +
Wide-view mode (WFOV mode) of Azure Kinect has extremely wide view angle:
 +
 
 +
<center><table border=0><tr>
 +
<td>[[Image:K4A-WFOV-scene-side-view.png|center|435px|Click to enlarge]]</td>
 +
<td width="15"></td>
 +
<td>[[Image:K4A-WFOV-scene-top-view.png|center|340px|Click to enlarge]]</td>
 +
</tr><tr>
 +
<td><center>'''Side view'''</center></td><td></td><td><center>'''Top view'''</center></td>
 +
</tr></table></center>
 +
 
 +
{{Note|But please be aware that quality of depth map is better in narrow-view mode (NFOV mode). For this reason, if you have enough space, it is recommended to use NFOV mode for Azure Kinect sensors.}}
 +
 
 +
==== First Generation Depth Sensor or Orbbec Astra (Pro) ====
 +
 
 +
If you're using outdated 1st generation depth sensor like Kinect v1 or Orbbec Astra (Pro) sensor which is almost the same as 1st gen. depth sensor:
 +
 
 
<center><table border=0><tr>
 
<center><table border=0><tr>
−
<td>[[Image:KSensor-scene-side-view.png|center|385px|Click to enlarge]]</td>
+
<td>[[Image:KSensor-scene-side-view.png|center|456px|Click to enlarge]]</td>
−
<td>[[Image:KSensor-scene-top-view.png|center|394px|Click to enlarge]]</td>
+
<td width="15"></td>
 +
<td>[[Image:KSensor-scene-top-view.png|center|453px|Click to enlarge]]</td>
 
</tr><tr>
 
</tr><tr>
−
<td><center>'''Side view'''</center></td><td><center>'''Top view'''</center></td>
+
<td><center>'''Side view'''</center></td><td></td><td><center>'''Top view'''</center></td>
 
</tr></table></center>
 
</tr></table></center>

Latest revision as of 08:18, 30 September 2019

Environment

Minimum space requirements for depth sensor configurations depend on sensor model and number of sensors:

Configuration Azure Kinect (WFOV mode) Azure Kinect (NFOV mode)
Kinect 2 (Kinect for Xbox One) 		1st gen. Depth Sensors
Orbbec Astra (Pro)
Single Depth Sensor

7 by 5 feet = 2 by 1.5 meters

8 by 5 feet = 2.5 by 1.5 meters

10 by 10 feet = 3 by 3 meters

2 Depth Sensors
(90-degrees config.)

7 by 7 feet = 2 by 2 meters

8 by 8 feet = 2.5 by 2.5 meters

10 by 10 feet = 3 by 3 meters

2 Depth Sensors
(180-degrees config.)

12 by 7 feet = 3.5 by 2 meters

16 by 8 feet = 5 by 2.5 meters

20 by 10 feet = 6 by 3 meters

3+ Depth Sensors

12 by 12 feet = 3.5 by 3.5 meters

16 by 16 feet = 5 by 5 meters

20 by 20 feet = 6 by 6 meters

Maximum capture area is about 7 by 7 feet ( = 2 by 2 meters), for all sensor models and configurations.

The pictures below will help you to understand possible capture area and required space. Dimensions are different for Azure Kinect, Kinect 2 (Kinect for Xbox One) and 1st gen. depth sensors due to different field of view.

Azure Kinect in NFOV mode and Kinect 2 for Windows (Kinect for Xbox One)

Kinect 2 (Kinect for Xbox One) sensors and Azure Kinect sensors in NFOV mode (narrow-view mode) have very close view angles (less than Azure Kinect in WFOV mode, but greater than 1st gen. depth sensors and Orbbec Astra):

Click to enlarge
Click to enlarge
Side view
Top view

Azure Kinect in WFOV mode

Wide-view mode (WFOV mode) of Azure Kinect has extremely wide view angle:

Click to enlarge
Click to enlarge
Side view
Top view
Note.png
Note: But please be aware that quality of depth map is better in narrow-view mode (NFOV mode). For this reason, if you have enough space, it is recommended to use NFOV mode for Azure Kinect sensors.

First Generation Depth Sensor or Orbbec Astra (Pro)

If you're using outdated 1st generation depth sensor like Kinect v1 or Orbbec Astra (Pro) sensor which is almost the same as 1st gen. depth sensor:

Click to enlarge
Click to enlarge
Side view
Top view
Retrieved from "http://docs.ipisoft.com/index.php?title=Recording_Video_from_Depth_Sensor_Environment&oldid=2142"