Object detection device and object detection method
Provided is an object detection device including: a detection unit configured to detect objects for every detection period to output detection information containing a reliability for each of the detected objects; a determination unit configured to: increment a detection count for each of the objects; calculate, for each of the objects, a sum of latest N reliabilities in the detection period; and determine, as a normally recognized object, an object for which the sum is equal to or larger than a first threshold value, which is set in advance depending on the detection count; and a control unit configured to output, as normally detected object information, detection information on the normally recognized object.
1. An object detection device, comprising:
a detection unit configured to detect one or more objects for every detection period to output detection information containing a reliability for each of the detected one or more objects;
a determination unit configured to:
increment a detection count for each of the one or more objects;
calculate, for each of the one or more objects, a sum of latest N reliabilities in the detection period, which are contained in the detection information; and
determine, as a normally recognized object, an object for which the sum is equal to or larger than a first threshold value, which is set in advance depending on the detection count; and
a control unit configured to output, as normally detected object information, detection information on an object determined to be the normally recognized object by the determination unit among objects contained in the detection information.
2. The object detection device according to claim 1 , wherein the determination unit is configured to, when the detection count from initial detection is M, which is smaller than N:
increment the detection count for each of the one or more objects;
calculate, for each of the one or more objects, a sum of M reliabilities from the initial detection, which are contained in the detection information; and
determine, as a normally recognized object, an object for which the sum is equal to or larger than a first threshold value, which is set in advance depending on the detection count.
3. The object detection device according to claim 1 , wherein the determination unit is configured to:
determine, as an erroneously recognized object, an object for which the sum is smaller than a second threshold value, which is set in advance depending on the detection count to be smaller than the first threshold value; and
delete information on the determined object from the detection information.
4. The object detection device according to claim 2 , wherein the determination unit is configured to:
determine, as an erroneously recognized object, an object for which the sum is smaller than a second threshold value, which is set in advance depending on the detection count to be smaller than the first threshold value; and
delete information on the determined object from the detection information.
5. An object detection method, comprising:
a first step of acquiring detection information containing a reliability for each object serving as a detection target for every detection period via a detector configured to output the detection information;
a second step of:
incrementing a detection count for each object;
calculating, for each object, a sum of latest N reliabilities in the detection period, which are contained in the detection information; and
determining, as a normally recognized object, an object for which the sum is equal to or larger than a first threshold value, which is set in advance depending on the detection count; and
a third step of outputting, as normally detected object information, detection information on an object determined to be the normally recognized object in the first step among objects contained in the detection information.
6. The object detection method according to claim 5 , wherein the second step further includes, when the detection count from initial detection is M, which is smaller than N:
incrementing the detection count for each object;
calculating, for each object, a sum of M reliabilities from the initial detection, which are contained in the detection information; and
determining, as a normally recognized object, an object for which the sum is equal to or larger than a first threshold value, which is set in advance depending on the detection count.
7. The object detection method according to claim 5 , wherein the second step further includes:
determining, as an erroneously recognized object, an object for which the sum is smaller than a second threshold value, which is set in advance depending on the detection count to be smaller than the first threshold value; and
deleting information on the determined object from the detection information.
8. The object detection method according to claim 6 , wherein the second step further includes:
determining, as an erroneously recognized object, an object for which the sum is smaller than a second threshold value, which is set in advance depending on the detection count to be smaller than the first threshold value; and
deleting information on the determined object from the detection information.