top of page
IMG_E4017.JPG
logo4header2.png

STEREOVISION

STEREOVISION MODULE WITH EMBEDDED DENSE DISPARITY PROCESSING
AND OBJECT DETECTION

Stereovision autonomics sweeper robots
stereovision.png

AUTONOMICS STEREOVISION high-quality 
3D vision for service robots. 

Last-mile delivery, warehousing, outdoor cleaning — robotization of these routines requires depth perception perform obstacle detection, visual odometry, SLAM.

Autonomics stereovision for autonomous street robots

Stereovision field trials

Stereocam field trials

Features

Features

1:

FPGA-based dense stereo disparity calculation along with embedded real-time subpixel-accuracy postprocessing makes AUTONOMICS STEREOVISION a perfectly suited solution for various applications.

2:

Built-in pedestrians and vehicle detection functions provided by state-of-the-art deep learning algorithms is an essential out-of-the-box feature for robots, operating in human-robot shared environment.

stereovision1.png

3:

Automotive-grade rugged design ensures the stability of stereo vision system calibration parameters even in severe operating conditions.

4:

ROS compatibility enables easy integration of AUTONOMICS STEREOVISION into existing systems.

ROS_cat.png

Specifications

Снимок2.JPG
Снимок3.JPG
Снимок5.JPG
Снимок4.JPG
Specifications
Camera

Sensor
Sensor resolution
Shutter control
Field of view: horizontal / vertical
Stereo baseline distance

Sony Pregius IMX 265, Color
1920 x 1080 pixels 
Global shutter
60° / 32°
342 mm

Embedded stereo processing

Embedded Stereo disparity pipeline

Embedded postprocessing

Erroneous pixels in non-occluded areas 
(with 3 pixels error threshold), %

Average disparity error 
in non-occluded areas, pixels

Density: percentage of pixels 
for which ground truth has been 
provided by the method, %

Stereo processing max performance

Disparity map resolution, pixels
Disparity range
Frame rate, FPS

FPGA-based: Census, multi-window 
aggregation, Semi-global Matching 
with 4 paths and two passes

Uniqueness check, WTA with subpixel 
accuracy (1/16), Consistency check

3.5

0.8

93

2 GDisp/sec

800х400   800x400     1200x600     1200x600
128              256              128                256
30               15                 20                  10

sensum_STEREOCAM_datasheet_chart.png

Object detection/recognition

Recognition objects

Output data

Frame rate, FPS

Vehicle, Pedestrian, 
Traffic Light (with signal recognition)

2D bounding box, class, confidence

10

Hardware details

Operating Voltage
Power Consumption
Dimensions
Weight
Interfaces
Shock load
Vibration load
Ambient operating temperature

9 – 36 V DC
< 40 W
392x100x32 mm
2 kg
Gigabit Ethernet, CAN
75g / 5 ms
5g / 5 Hz – 500 Hz
-50 °C ... +50 °C

Dimensions

sensum_STEREOCAM_datasheet_dims.png
Stereocam datasheet

Discover RADAR

RADAR

Software-defined mmWave 4D imaging radar

for service robots.

radar.png
bottom of page