CN-121995356-A - Method and device for determining occupied position in space

Abstract

Methods and apparatus are provided for determining an occupied location in a space. The method starts with the detection of the movement of the object received from the radar monitoring the space. Each detection is associated with a location in space and a point in time when the detection was made. The method accumulates detections at time points within a first time period having a predetermined duration and identifies a set of detected clusters in space by analyzing the similarity of the accumulated detections in terms of location. Any clusters whose detection is temporally distributed within a proportion of the first time period below a predetermined proportion threshold are then removed from the set of clusters. The locations in space corresponding to the set of clusters are determined to be occupied during a first period of time.

Inventors

• Christopher Xie Ersong

Assignees

• 安讯士有限公司

Dates

Publication Date

20260508

Application Date

20251107

Priority Date

20241107

Claims (14)

1. 1. A method for determining an occupied location in a space, comprising: receiving (S02) detections of object movements from a radar monitoring said space, wherein each detection is associated with a position in said space and a point in time when said detection is performed, wherein said detections received comprise detections from a plurality of points in time corresponding to a plurality of frames of radar data, Accumulating (S04) a detection of a point in time within a first time period (T1) having a predetermined duration, wherein the first time period (T1) of the predetermined duration comprises a number of frames of radar data, Identifying (S06) a set of detected clusters in the space (502 a, 502 b) by analyzing the accumulated similarity of the detections (502) in terms of location, wherein each cluster comprises a plurality of detections made at different points in time during the first time period (T1), Removing (S08) any clusters from the set of clusters, the detection of which is temporally distributed in a proportion of the first time period (T1) below a predetermined proportion threshold, and After the removing, it is determined (S10) that a position in the space corresponding to the set of clusters is occupied during the first time period (T1).
2. 2. The method according to claim 1, wherein each detection is further associated with a speed of movement of the object, and wherein in the step of accumulating (S04) only detections having a speed below a first speed threshold are accumulated.
3. 3. The method of claim 2, wherein the first speed threshold is lower than an average walking speed of the person.
4. 4. The method according to claim 1, wherein the step of removing (S08) further comprises removing any of the following clusters from the set of clusters: The time correlation between the detection of the cluster and the detection of another cluster in the set of clusters is above a time correlation threshold, and The distance from the detection of the radar of the cluster is greater than the distance from the detection of the radar of the other cluster.
5. 5. The method according to claim 1, wherein the proportion of the detection of clusters of the first time period (T1) within which the detection of clusters is temporally distributed is determined as the proportion of the detection of clusters during the first time period (T1).
6. 6. The method according to claim 1, wherein the proportion of the first time period (T1) within which the detection of clusters is distributed in time is determined by comparing a dispersion measure of the time points of the detection of clusters with the predetermined duration of the first time period.
7. 7. The method according to claim 1, wherein the step of identifying (S06) a set of detected clusters in the space (502 a, 502 b) comprises applying a clustering algorithm to the accumulated positions of the detections (502).
8. 8. The method according to claim 1, wherein the step of identifying (S06) a set of detected clusters in the space (502 a, 502 b) comprises: Generating an occupancy map (600) of the space by defining a plurality of grid cells in the space and counting for each grid cell how many of the accumulated detections (502) have positions in the grid cells, and The set of clusters is identified by performing spot detection in the occupancy map (600) of the space.
9. 9. The method of claim 8, wherein the blob detection includes identifying local maxima in the occupancy map (600).
10. 10. The method of claim 1, wherein the method is repeated for a subsequent time period of a predetermined duration.
11. 11. The method of claim 10, further comprising: The position in the space determined to be occupied between the first time period (T1) and the subsequent time period is tracked.
12. 12. The method of claim 11, further comprising: The trajectories outside the region of interest in the space are removed.
13. 13. An apparatus for determining an occupied location in a space, wherein the apparatus comprises circuitry configured to: Receiving detections of object movement from a radar (108) monitoring the space (100), wherein each detection is associated with a location in the space (100) and a point in time when the detection is performed, wherein the received detections comprise detections from a plurality of points in time corresponding to a plurality of frames of radar data, Accumulating a detection of a point in time within a first time period (T1) having a predetermined duration, wherein the first time period (T1) of the predetermined duration comprises a number of frames of radar data, Identifying a set of detected clusters in the space (502 a, 502 b) by analyzing the accumulated similarities in position of the detections (502), wherein each cluster comprises a plurality of detections made at different points in time during the first time period (T1), Removing from the set of clusters any clusters (700 b) whose detection is temporally distributed within a proportion of the first time period (T1) below a predetermined proportion threshold, and After the removing, it is determined that a location in the space corresponding to the set of clusters is occupied during the first time period (T1).
14. 14. A non-transitory computer readable medium comprising computer program code which, when executed by an apparatus having processing capabilities, causes the apparatus to perform the method of any one of claims 1 to 12.

Description

Method and device for determining occupied position in space Technical Field The present invention relates to the field of occupancy detection in space. In particular, the present invention relates to a method and system for determining the location of occupied space by using radar technology. Background In various environments, such as offices, public spaces, or industrial facilities, it is often valuable to know the number of people present and their spatial location in the environment. Such information can be used to optimize resource allocation and improve operating efficiency. For example, in an office environment, understanding which desks are occupied and how long they are occupied can help facility managers optimize desk layout, reduce energy consumption, and increase employee productivity. However, due to concerns about personal privacy, conventional methods for determining occupancy, such as analyzing images captured by surveillance cameras, may not always be viable. Radar technology offers a promising alternative to detect occupancy without compromising personal privacy. By emitting radio waves and measuring the reflection, the radar system can detect the presence and location of objects within a given space. The challenge in occupancy detection is to distinguish between locations in a space that are occupied for a long period of time (e.g., desks occupied by individuals) and temporary presence in the space (e.g., individuals passing through the space). It is therefore desirable to detect the position of objects left at the same position for a period of time and ignore other temporarily existing objects. To address these problems, there is therefore a need for a reliable method that can accurately detect occupied locations within a scene using radar technology. This approach will ensure the identification of areas that are occupied for a long period of time while still respecting personal privacy. Disclosure of Invention In view of the above, it is therefore an object of the present invention to alleviate the above problems and to provide a method and apparatus which allow determining the occupied position in a scene by using detection from radar. According to a first aspect, the above object is achieved by a method for determining an occupied position in a space. The method comprises the following steps: Detecting movement of an object is received from a radar monitoring a space, wherein each detection is associated with a position in the space and a point in time when the detection is performed, The detection of a point in time within a first period of time having a predetermined duration is accumulated, Identifying a set of detected clusters in space by analyzing the accumulated similarity of the detections in terms of location, Removing any clusters whose detection is temporally distributed within a proportion of the first time period below a predetermined proportion threshold from the set of clusters, an A location in space corresponding to a set of clusters is determined to be occupied during a first period of time. The present invention relies on the idea that even if a movable object remains at the same location within the environment, it will from time to time make small movements, referred to herein as micro-movements. For example, a person sitting at a desk will make some movements with the arms, torso and head while working. These movements may be detected by the radar and will be located at approximately the same location in space, but will typically not be detected by the radar as often. However, if radar detection is accumulated over a period of time, detection from movable objects left at the same location will form clusters in space. This is in contrast to the movement of an object moving around in space (i.e. changing its position). That movement will be distributed over a larger area in space. Thus, when radar detection accumulates over time, the detection from objects moving around in space will typically be dispersed in space and not form clusters. Thus, over time, the detected accumulation is combined with spatial clustering, allowing moveable objects that may remain at the same position for a longer period of time (i.e. during the first period of time) to be distinguished from objects that move around in space. Moreover, even if the detection of an object moving around in space happens to form clusters in space, e.g. due to a short dwell of the object in a certain position, the detection in the clusters will be limited to a time window that is short relative to the first time period. Therefore, it is preferable to remove any spatial clusters whose associated radar detection is distributed in time during a limited proportion of the first period of time. In this way, the risk is reduced that objects that stay briefly while passing through space are mistaken for objects that remain in the same position for a longer period of time. The occupied position in the space generally m