This is machine translation

Translated by Microsoft
Mouseover text to see original. Click the button below to return to the English version of the page.

Note: This page has been translated by MathWorks. Click here to see
To view all translated materials including this page, select Country from the country navigator on the bottom of this page.


Partition detections based on Mahalanobis distance

Using multiple distance thresholds, the function separates detections into different detection cells based on their relative Mahalanobis distances and reports all the possible partitions. A partition of a set of detections is defined as a division of these detections into nonempty mutually exclusive detection cells. A detection cell is a group of detections whose distance to at least one other detection in the cell is less than the distance threshold. In other words, two detections belong to the same detection cell if their distance is less than the distance threshold.


partitions = partitionDetections(detections)
partitions = partitionDetections(detections,tLower,tUpper)
partitions = partitionDetections(detections,tLower,tUpper,'MaxNumPartitions',maxNumber)
partitions = partitionDetections(detections,allThresholds)



partitions = partitionDetections(detections) returns possible partitions from detections, using distance partitioning algorithm. By default, the function considers all real value Mahalanobis distance thresholds between 0.5 and 6.25.

partitions = partitionDetections(detections,tLower,tUpper) allows you to specify the lower and upper bounds of the distance thresholds, tLower and tUpper.

partitions = partitionDetections(detections,tLower,tUpper,'MaxNumPartitions',maxNumber) allows you to specify the maximum number of allowed partitions, maxNumber, in addition to the lower and upper bounds of the distance thresholds, tLower and tUpper.

partitions = partitionDetections(detections,allThresholds) allows you to specify the exact thresholds considered for partition.


collapse all

Generate 2-D detections using objectDetection.

rng(2018); % For reproducible results
detections = cell(10,1);
for i = 1:numel(detections)
    id = randi([1 5]);
    detections{i} = objectDetection(0,[id;id] + 0.1*randn(2,1));
    detections{i}.MeasurementNoise = 0.01*eye(2);

Extract and display generated position measurements.

d = [detections{:}];
measurements = [d.Measurement];


Generate partitions from the detections and count the number of partitions.

partitions = partitionDetections(detections);
numPartitions = size(partitions,2);

Visualize the partitions. Each color represents a detection cell.

for i = 1:numPartitions
    numCells = max(partitions(:,i));
    for k = 1:numCells
        ids = partitions(:,i) == k;
        hold on;
    title(['Partition ',num2str(i),' (',num2str(k),' Detection cells)']);

Input Arguments

collapse all

Object detections, specified as an N-element cell array of objectDetection objects, where N is the number of detections. You can create detections directly, or you can obtain detections from the outputs of sensor objects, such as radarSensor, monostaticRadarSensor, irSensor, and sonarSensor.

Data Types: cell

Lower bound of distance thresholds, specified as a scalar. This argument sets the lower bound of the Mahalanobis distance thresholds considered for partition.

Example: 0.05

Data Types: double

Upper bound of distance thresholds, specified as a scalar. This argument sets the upper bound of the Mahalanobis distance thresholds considered for partition.

Example: 0.98

Data Types: double

Maximum number of allowed partitions, specified as a positive integer.

Example: 20

Data Types: double

All thresholds for partitions, specified as an M element vector. The function calculates partitions based on each threshold value provided in allThresholds. Note that multiple thresholds can result in the same partition, and the function output partitions, given as an N-by-Q matrix with QM, only contains unique partitions.

Example: [0.1;0.2;0.35;0.4]

Data Types: double

Output Arguments

collapse all

Partitions of detections, specified as an N-by-Q matrix. N is the number of detections, and Q is the number of partitions. Each column of the matrix represents a valid partition. In each column, the value of the ith element represents the identity number of the detection cell that the ith detection belongs to. For example, given a partition matrix P, if P(i,j) = k, then in partition j, detection i belongs to detection cell k.


[1] Granstorm, K., C. Lundquiest, and O. Orguner. " Extended target tracking using a Gaussian-mixture PHD filter." IEEE Transactions on Aerospace and Electronic Systems. Vol. 48, Number 4, 2012, pp. 3268–3286.

Extended Capabilities

Introduced in R2019a