Intrusion detection method and apparatus
An intrusion detection method includes obtaining a first point cloud from a light detection and ranging (LiDAR) sensor, obtaining a first object information by applying a first perception process to the first point cloud, modifying the first point cloud to obtain a second point cloud, obtaining a second object information by applying a second perception process to the second point cloud, and providing an intrusion result based on a comparison between the first object information and the second object information.
1 . An intrusion detection method, comprising:
obtaining a first point cloud of an object from a light detection and ranging (LiDAR) sensor;
obtaining first object information regarding the object by applying a first perception process to the first point cloud, wherein the first object information comprises a confidence score indicating a probability that the object is accurately recognized;
modifying the first point cloud to obtain a second point cloud of the object;
obtaining second object information regarding the object by applying a second perception process to the second point cloud, wherein the second object information comprises a confidence score indicating a probability that the object is accurately recognized;
making a comparison between the first object information and the second object information and an object information threshold; and
providing an intrusion result based on the comparison between the first object information and the second object information being equal to or greater than the object information threshold.
2 . The intrusion detection method of claim 1 , wherein modifying the first point cloud to obtain the second point cloud comprises adding one or more points to the first point cloud.
3 . The intrusion detection method of claim 2 , further comprising locating the one or more points by deep reinforcement learning.
4 . The intrusion detection method of claim 1 , further comprising:
classifying the first object information as an intrusion when the comparison between the first object information and the second object information is equal to or greater than the object information threshold; or
classifying the first object information as benign when the comparison between the first object information and the second object information is less than the object information threshold.
5 . The intrusion detection method of claim 4 , further comprising dropping the first object information.
6 . The intrusion detection method of claim 1 , further comprising forwarding the first object information to a planning module.
7 . The intrusion detection method of claim 1 , wherein the first object information and the second object information each comprise a location of the object.
8 . An intrusion detection apparatus, comprising:
one or more memories configured to store programming instructions; and
at least one processor coupled to the one or more memories and configured to execute the programming instructions to cause the apparatus to:
obtain a first point cloud of an object from a light detection and ranging (LiDAR) sensor;
obtain a first object information regarding the object by applying a first perception process to the first point cloud, wherein the first object information comprises a confidence score indicating a probability that the object is accurately recognized;
modify the first point cloud to obtain a second point cloud of the object;
obtain a second object information regarding the object by applying a second perception process to the second point cloud, wherein the second object information comprises a confidence score indicating a probability that the object is accurately recognized;
make a comparison between the first object information and the second object information and an object information threshold; and
provide an intrusion result based on the comparison between the first object information and the second object information being equal to or greater than the object information threshold.
9 . The intrusion detection apparatus of claim 8 , wherein the at least one processor is further configured to execute the programming instructions to cause the apparatus to remove one or more points from the first point cloud.
10 . The intrusion detection apparatus of claim 9 , wherein the at least one processor is further configured to execute the programming instructions to cause the apparatus to locate the one or more points by deep reinforcement learning.
11 . The intrusion detection apparatus of claim 8 wherein the at least one processor is further configured to execute the programming instructions to cause the apparatus to:
classify the first object information as an intrusion when the comparison between the first object information and the second object information is equal to or greater than the object information threshold.
12 . The intrusion detection apparatus of claim 11 , wherein the at least one processor is further configured to execute the programming instructions to cause the apparatus to forward a corrected object information to a planning module, wherein the corrected object information is based on the second object information.
13 . The intrusion detection apparatus of claim 8 , wherein the at least one processor is further configured to execute the programming instructions to cause the apparatus to forward the first object information to a planning module.
14 . The intrusion detection apparatus of claim 8 , wherein the first object information and the second object information each comprise a volume of the object.
15 . A computer program product comprising instructions stored on a non-transitory medium that, when executed by one or more a processors, cause an apparatus to:
obtain a first point cloud of an object from a light detection and ranging (LiDAR) sensor;
obtain a first object information regarding the object by applying a first perception process to the first point cloud, wherein the first object information comprises a confidence score indicating a probability that the object is accurately recognized;
modify the first point cloud to obtain a second point cloud of the object;
obtain a second object information regarding the object by applying a second perception process to the second point cloud, wherein the second object information comprises a confidence score indicating a probability that the object is accurately recognized;
make a comparison between the first object information and the second object information and an object information threshold; and
provide an intrusion result based on the comparison between the first object information and the second object information being equal to or greater than the object information threshold.
16 . The computer program product of claim 15 , wherein the instructions, when executed by the one or more processors further cause the apparatus to modify the first point cloud to obtain the second point cloud by:
adding one or more points to the first point cloud, or
removing one or more points from the first point cloud.
17 . The computer program product of claim 16 , wherein the instructions, when executed by the one or more processors, further cause the apparatus to locate the one or more points by deep reinforcement learning.
18 . The computer program product of claim 15 , wherein the instructions, when executed by the one or more processors, further cause the apparatus to perform at least one of:
drop the first object information, or
forward a corrected object information to a planning module, wherein the corrected object information is based on the second object information.
19 . The computer program product of claim 15 , wherein the instructions, when executed by the one or more processors, further cause the apparatus to provide an intrusion result based on a comparison between the first object information and the second object information by classifying the first object information as benign when the comparison between the first object information and the second object information is less than the object information threshold.