Familiarity degree estimation apparatus, familiarity degree estimation method, and recording medium
In a familiarity degree estimation apparatus, a first video process unit calculates a time while a hand being viewed, which is a time when a customer is viewing the hand. A second video process unit calculates a time while an item being held, which is a time when the customer is holding an item. A familiarity degree estimation unit calculates a time while the item being viewed based on the time while a hand being viewed and the time while the item being held, and estimates that the longer the time while the item being viewed, the lower the degree of familiarity of the customer with respect to the item.
1 . A system comprising:
a line-of-sight camera disposed above an item shelf and configured to capture a video of a customer in front of the item shelf, including a face of the customer;
a first item camera disposed on a left portion of the item shelf and including a first illumination unit at a bottom of the item shelf, the first item camera and configured to capture a video of the item shelf in an upper right direction while the first illumination unit is illuminating the item shelf in the upper right direction, the video including a hand of the customer taking or putting back an item from the item shelf;
a second item camera disposed on a right portion of the item shelf and including a second illumination unit at a top of the item shelf, the second item camera and configured to capture a video of the item shelf in a lower left direction while the second illumination unit is illuminating the item shelf in the lower left direction, the video including the hand of the customer taking or putting back the item from the item shelf, wherein the second item camera is vertically higher than the first item camera;
a memory storing instructions; and
one or more processors configured to execute the instructions to:
calculate a time while a hand is being viewed by a customer, based on the video of the customer captured by the line-of-sight camera;
calculate a time while an item is being held by the customer, based on the videos of the item shelf captured by the first and second item cameras; and
estimate a degree of familiarity of the customer with respect to the item based on the time while the hand is being viewed and the time while the item is being held,
wherein disposition of the first and second item cameras on the left and right portions of the item shelf, respectively, where the second item camera is vertically higher than the first item camera, ensures that the item is included in the video captured by one of the first and second item cameras includes the item even when the item is hidden by the hand of the customer in the video captured by another of the first and second item cameras.
2 . The familiarity degree estimation apparatus according to claim 1 ,
wherein the processor recognizes the item from the videos captured by the first and second item cameras; and
wherein the processor stores the degree of familiarity in association with the recognized item.
3 . The familiarity degree estimation apparatus according to claim 1 , wherein the processor calculates a time while the item is being viewed, based on the time while the hand is being viewed and the time while the item is being held, and estimates the degree of familiarity based on the time while the item is being viewed.
4 . The familiarity degree estimation apparatus according to claim 3 , wherein the processor estimates that the longer the time while the item is being viewed, the lower the degree of familiarity, and the shorter the time while the item is being viewed, the higher the degree of familiarity.
5 . The familiarity degree estimation apparatus according to claim 4 , wherein the processor calculates a reciprocal of the time while the item is being viewed as the degree of familiarity.
6 . The familiarity degree estimation apparatus according to claim 1 ,
wherein the processor determines attributes of the customer based on at least one of the video captured by the line-of-sight customer and the videos captured by the first and second item cameras; and
wherein the processor stores the degree of familiarity in a manner classified into the attributes of the customer.
7 . The familiarity degree estimation apparatus according to claim 1 , wherein the processor acquires information of whether or not the customer purchased the item, and stores the degree of familiarity in a manner classified into a case where the customer purchased the item and a case where the customer did not purchase the item.
8 . A familiarity degree estimation method performed by a system and comprising:
capturing, by a line-of-sight camera of the system and disposed above an item shelf, a video of a customer in front of the item shelf, including a face of the customer;
capturing, by a first item camera of the system disposed on a left portion of the item shelf and including a first illumination unit at a bottom of the item shelf, a video of the item shelf in an upper right direction while the first illumination unit is illuminating the item shelf in the upper right direction, the video including a hand of the customer taking or putting back an item from the item shelf;
capturing, by a second item camera disposed on a right portion of the item shelf and including a second illumination unit at a top of the item shelf, a video of the item shelf in a lower left direction while the second illumination unit is illuminating the item shelf in the lower left direction, the video including the hand of the customer taking or putting back the item from the item shelf, wherein the second item camera is vertically higher than the first item camera;
calculating, by one or more processors of the system, a time while a hand is being viewed when a customer is viewing the hand, based on the video of the customer captured by the line-of-sight camera;
calculating, by one or more processors of the system, a time while an item is being held when the customer is holding the item, based on the videos of the item shelf captured by the first and second item cameras; and
estimating, by one or more processors of the system, a degree of familiarity of the customer with respect to the item based on the time while the hand is being viewed and the time while the item is being held,
wherein disposition of the first and second item cameras on the left and right portions of the item shelf, respectively, where the second item camera is vertically higher than the first item camera, ensures that the item is included in the video captured by one of the first and second item cameras includes the item even when the item is hidden by the hand of the customer in the video captured by another of the first and second item cameras.
9 . The familiarity degree estimation method according to claim 8 , further comprising:
recognizing the item from the videos captured by the first and second item cameras; and
storing the degree of familiarity in association with the recognized item.
10 . The familiarity degree estimation method according to claim 8 , wherein estimating the degree of familiarity comprises:
calculating a time while the item is being viewed, based on the time while the hand is being viewed and the time while the item is being held; and
estimating the degree of familiarity based on the time while the item is being viewed.
11 . The familiarity degree estimation method according to claim 10 , wherein estimating the degree of familiarity estimates that the longer the time while the item is being viewed, the lower the degree of familiarity, and the shorter the time while the item is being viewed, the higher the degree of familiarity.
12 . The familiarity degree estimation method according to claim 11 , wherein estimating the degree of familiarity calculates a reciprocal of the time while the item is being viewed as the degree of familiarity.
13 . The familiarity degree estimation method according to claim 8 , further comprising:
determining attributes of the customer based on at least one of the video captured by the line-of-sight customer and the videos captured by the first and second item cameras; and
storing the degree of familiarity in a manner classified into the attributes of the customer.
14 . The familiarity degree estimation method according to claim 8 , further comprising:
acquiring information of whether or not the customer purchased the item; and
storing the degree of familiarity in a manner classified into a case where the customer purchased the item and a case where the customer did not purchase the item.
15 . A non-transitory computer-readable recording medium storing a program executable by a computer to perform processing comprising:
capturing, by a line-of-sight camera of the system and disposed above an item shelf, a video of a customer in front of the item shelf, including a face of the customer;
capturing, by a first item camera of the system disposed on a left portion of the item shelf and including a first illumination unit at a bottom of the item shelf, a video of the item shelf in an upper right direction while the first illumination unit is illuminating the item shelf in the upper right direction, the video including a hand of the customer taking or putting back an item from the item shelf;
capturing, by a second item camera disposed on a right portion of the item shelf and including a second illumination unit at a top of the item shelf, a video of the item shelf in a lower left direction while the second illumination unit is illuminating the item shelf in the lower left direction, the video including the hand of the customer taking or putting back the item from the item shelf, wherein the second item camera is vertically higher than the first item camera;
calculating, by one or more processors of the system, a time while a hand is being viewed when a customer is viewing the hand, based on the video of the customer captured by the line-of-sight camera;
calculating, by one or more processors of the system, a time while an item is being held when the customer is holding the item, based on the videos of the item shelf captured by the first and second item cameras; and
estimating, by one or more processors of the system, a degree of familiarity of the customer with respect to the item based on the time while the hand is being viewed and the time while the item is being held,
wherein disposition of the first and second item cameras on the left and right portions of the item shelf, respectively, where the second item camera is vertically higher than the first item camera, ensures that the item is included in the video captured by one of the first and second item cameras includes the item even when the item is hidden by the hand of the customer in the video captured by another of the first and second item cameras.