Person tracking system, person tracking method, and storage medium
In a person tracking system, a calculation processing means performs processing for detecting a first person from an image, and calculates a first feature vector representing a feature of the detected first person. A data transmission processing means acquires a hash value corresponding to a key generated based on information relating to the first feature vector, and stores feature data including the first feature vector and the key in a storage area of an external device determined based on the acquired hash value. A determination processing means determines whether or not the first person represented by the first feature vector included in the feature data read from the external device and a second person registered in advance are the same person. A tracking processing means tracks the first person as a tracking target, when it is determined that the first person and the second person are the same person.
1 . A person tracking system comprising:
a memory configured to store instructions; and
a processor configured to execute the instructions to:
perform processing for detecting a first person from an image, and calculate a first feature vector representing a feature of the detected first person;
acquire a hash value corresponding to a key generated based on information relating to the first feature vector, and store feature data including the first feature vector and the key in a storage area of an external device determined based on the acquired hash value;
determine whether or not the first person represented by the first feature vector included in the feature data read from the external device and a second person registered in advance are a same person; and
track the first person as a tracking target, when it is determined that the first person and the second person are the same person.
2 . The person tracking system according to claim 1 , wherein the processor determines whether or not the first person and the second person are the same person, based on a distance between a first hash value and a second hash value, the first hash value being calculated by performing a predetermined stochastic calculation on the first feature vector, and the second hash value being calculated by performing the predetermined stochastic calculation on a second feature vector corresponding to a representative vector that best represents a feature of the second person.
3 . The person tracking system according to claim 2 , wherein, when it is determined that the first person and the second person are not the same person, the processor performs stochastic processing for acquiring a third feature vector using a plurality of feature vectors representing the feature of the second person by vectors different from the second feature vector, and performs re-determination as to whether or not the first person and the second person are the same person based on a distance between the first hash value and a third hash value, the third hash value being calculated by performing the predetermined stochastic calculation on the third feature vector.
4 . The person tracking system according to claim 3 , wherein, when it is determined by the re-determination that the first person and the second person are the same person, the processor updates the representative vector from the second feature vector to the third feature vector.
5 . The person tracking system according claim 2 , wherein the predetermined stochastic calculation is a calculation using locality sensitive hashing.
6 . A person tracking method comprising:
performing processing for detecting a first person from an image, and calculating a first feature vector representing a feature of the detected first person;
acquiring a hash value corresponding to a key generated based on information relating to the first feature vector, and storing feature data including the first feature vector and the key in a storage area of an external device determined based on the acquired hash value;
determining whether or not the first person represented by the first feature vector included in the feature data read from the external device and a second person registered in advance are a same person; and
tracking the first person as a tracking target, when it is determined that the first person and the second person are the same person.
7 . A non-transitory computer-readable recording medium recording a program, the program causing a computer to execute:
performing processing for detecting a first person from an image, and calculating a first feature vector representing a feature of the detected first person;
acquiring a hash value corresponding to a key generated based on information relating to the first feature vector, and storing feature data including the first feature vector and the key in a storage area of an external device determined based on the acquired hash value;
determining whether or not the first person represented by the first feature vector included in the feature data read from the external device and a second person registered in advance are a same person; and
tracking the first person as a tracking target, when it is determined that the first person and the second person are the same person.