| Short Name | RSSP |
| Long Name | RSSP |
| Website | |
| Description | A real-time semantic 3D scene parsing system for LiDAR sensors. The proposed system only uses the coordinates of 3D points which are direct outputs of standard laser scanners, and no color information is involved. The submitted runtime includes preprocessing(305s), STNet(7s) and CRF(47s). The voxel size is 2cm and all implementations are based on Python and Tensorflow. |
| Reference | Anonymous submission |
| Hardware | Intel® core(TM) CPU i5-4590 @ 3.3 GHZ, 8 GB RAM, GTX 1080 |
| Used additional training data | 0 |
| Last submission | 2018-08-25 09:59:47 |
| Is opensource | 0 |
| Number of submissions | 1 |
| A_IoU | OA | [s] | IoU 1 | IoU 2 | IoU 3 | IoU 4 | IoU 5 | IoU 6 | IoU 7 | IoU 8 | |
| Result | 0.647 | 0.920 | 359.00 | 0.916 | 0.870 | 0.870 | 0.525 | 0.930 | 0.158 | 0.320 | 0.589 |
| Rank | 50 | 42 | 43 | 44 | 37 | 19 | 15 | 45 | 64 | 56 | 58 |
| L1' | L2' | L3' | L4' | L5' | L6' | L7' | L8' | |
| L1 | 13999611 | 157171 | 55 | 39412 | 58685 | 31266 | 17566 | 13743 |
| L2 | 711783 | 9611037 | 8579 | 228827 | 6432 | 109194 | 11457 | 7437 |
| L3 | 1782 | 1303 | 4603534 | 21302 | 1852 | 19342 | 26054 | 702 |
| L4 | 24882 | 150268 | 571761 | 1973096 | 93348 | 131607 | 66334 | 10598 |
| L5 | 105966 | 2792 | 10622 | 143464 | 30363098 | 223129 | 45948 | 16187 |
| L6 | 75432 | 22274 | 25852 | 259753 | 1423438 | 464946 | 38187 | 74663 |
| L7 | 8228 | 437 | 740 | 1532 | 40639 | 33111 | 148789 | 363 |
| L8 | 43569 | 23339 | 779 | 45634 | 118725 | 19626 | 25865 | 574405 |