Data compression system and method of using
A system includes a non-transitory computer readable medium configured to store instructions thereon; and a processor connected to the non-transitory computer readable medium. The processor is configured to execute the instructions for generating a mask based on received data from a sensor, wherein the mask includes a plurality of importance values, and each region of the received data is designated a corresponding importance value of the plurality of importance values. The processor is configured to execute the instructions for encoding the received data based on the mask; and transmitting the encoded data to a decoder for defining reconstructed data. The processor is configured to execute the instructions for computing a loss based on the reconstructed data, the received data and the mask. The processor is configured to execute the instructions for providing training to an encoder for encoding the received data based on the computed loss.
1. A system comprising:
a non-transitory computer readable medium configured to store instructions thereon; and
a processor connected to the non-transitory computer readable medium, wherein the processor is configured to execute the instructions for:
generating a mask based on received data from a sensor, wherein the mask includes a plurality of importance values, and each region of the received data is designated a corresponding importance value of the plurality of importance values;
encoding the received data based on the mask;
transmitting the encoded data to a decoder for defining reconstructed data;
computing a loss based on the reconstructed data, the received data and the mask; and
providing training to an encoder for encoding the received data based on the computed loss.
2. The system according to claim 1 , wherein the processor is further configured to execute the instructions for:
decoding the received data to define the reconstructed data.
3. The system according to claim 1 , wherein the processor is further configured to execute the instructions for:
generating the mask based on a proximity of detected objects to the sensor.
4. The system according to claim 1 , wherein the processor is further configured to execute the instructions for:
generating the mask based on detected movement of detected objects based on the received data.
5. The system according to claim 1 , wherein the processor is further configured to execute the instructions for:
generating the mask based on a classification of each of the detected objects in the received data.
6. The system according to claim 1 , wherein the processor is further configured to execute the instructions for:
generating a ground truth mask based on the received data and ground truth segments.
7. The system according to claim 6 , wherein the processor is further configured to execute the instructions for:
computing the loss further based on the ground truth mask.
8. The system according to claim 1 , wherein the processor is further configured to execute the instructions for:
detecting objects in the reconstructed data.
9. The system according to claim 8 , wherein the processor is further configured to execute the instructions for:
computing the loss further based on the detected objects in the reconstructed data.
10. The system according to claim 1 , wherein the sensor comprises a light detection and ranging (LiDAR) sensor.
11. The system according to claim 1 , wherein the processor comprises a plurality of processors, a first processor of the plurality of processors is at an encoder location, and a second processor of the plurality of processors is at a decoder location different from the encoder location.
12. A method comprising:
generating a mask, using a processor, based on received data from a sensor, wherein the mask includes a plurality of importance values, and each region of the received data is designated a corresponding importance value of the plurality of importance values;
encoding the received data based on the mask;
transmitting the encoded data to a decoder for defining reconstructed data;
computing a loss based on the reconstructed data, the received data and the mask; and
providing training to an encoder for encoding the received data based on the computed loss.
13. The method according to claim 12 , further comprising:
decoding the received data to define the reconstructed data.
14. The method according to claim 12 , wherein generating the mask comprises generating the mask based on a proximity of detected objects to the sensor.
15. The method according to claim 12 , wherein generating the mask comprises generating the mask based on detected movement of detected objects based on the received data.
16. The method according to claim 12 , wherein generating the mask comprises generating the mask based on a classification of each of the detected objects in the received data.
17. The method according to claim 12 , further comprising:
generating a ground truth mask based on the received data and ground truth segments.
18. The method according to claim 17 , wherein computing the loss further comprises computing the loss based on the ground truth mask.
19. The method according to claim 18 , further comprising:
detecting objects in the reconstructed data.
20. The method according to claim 19 , wherein computing the loss further comprises computing the loss based on the detected objects in the reconstructed data.