An inventory tracking scaled locking canister has a housing, a closure, a commodity container positioned within the housing and releasably sealed within the housing by the closure through an electrically disengageable magnetic locking mechanism, at least one weight sensor, a processing unit, a biometric sensor, a digital display, a data storage unit, a wireless communication device, a power source, and a GPS module. The commodity container may have multiple nested frames with perforations that allow smaller byproducts of the contents of the central frame to be separated from the bulk of the contents. The weight of each frame is measured individually through one or more load cells. The biometric sensor prevents unauthorized access to the commodity container. The processing unit facilitates data collection, storage, and transmittal through the wireless communication device to a remote server. The GPS module tracks the location of the canister in case of theft.

A tracking system includes a camera subsystem that includes cameras that capture vide of a space. Each camera is coupled with a camera client that determines local coordinates of people in the captured video. The camera clients generate frames that include color frames and depth frames labeled with an identifier number of the camera and their corresponding timestamps. The camera clients generate tracks that include metadata describing historical people detections, tracking identifications, timestamps, and the identifier number of the camera. The camera clients send the frames and tracks to cluster servers that maintain the frames and tracks such that they are retrievable using their corresponding labels. A camera server queries the cluster servers to receive the frames and tracks using their corresponding labels. The camera server determines the physical positions of people in the space based on the determined local coordinates.

A goods sensing system includes: a sample collector that collects a plurality of sets of image samples, where each set of the image samples comprise sample images of a type of goods at multiple angles, where a set of the image samples of a same type of goods are provided with a same group identification, and the group identification is the type of the goods corresponding to the set of image samples; a model trainer that trains a convolutional neural network model according to each sample image and a group identification of the sample image to obtain a goods identification model; a real-time image collector that continuously acquires at least one real-time image of space in front of a shelf, each real-time image including part or all of images of goods; and a goods category deriver that obtains a type and quantity of the goods displayed in the real-time.

A vending machine (100) and a vending method and vending system (1000) therefor, the vending machine (100) comprising a machine body (10), a door body (20), and at least one layer of shelves (30) and a weighing device (40) that are installed inside the machine body (10). The vending method comprises: collecting the weight of products on a shelf before and after vending (S1); calculating the difference of the change between the weight of the products on the shelf before vending and the weight of the products on the shelf after vending (S2); and if the difference of the change is less than a first weight change threshold, issuing an alarm prompt (S3), wherein the first weight change threshold is less than or equal to zero. Using the present invention may promptly determine the misplacement and replacement of the products without relying on an RFID tag.

A tracking system includes a camera subsystem that includes cameras that capture vide of a space. Each camera is coupled with a camera client that determines local coordinates of people in the captured video. The camera clients generate frames that include color frames and depth frames labeled with an identifier number of the camera and their corresponding timestamps. The camera clients generate tracks that include metadata describing historical people detections, tracking identifications, timestamps, and the identifier number of the camera. The camera clients send the frames and tracks to cluster servers that maintain the frames and tracks such that they are retrievable using their corresponding labels. A camera server queries the cluster servers to receive the frames and tracks using their corresponding labels. The camera server determines the physical positions of people in the space based on the determined local coordinates.

An item position tracking system includes weight sensors each associated with a weight board. Each weight sensor transmits sensor data indicative of a weight of an item to its corresponding weight board. Each weight board is configured to assign a particular address number to its corresponding weight sensor. The weight boards transmit the sensor data and the address numbers to a circuit board that transmits the sensor data and the address numbers to a weight server. The weight server determines from which weight sensor data is originated based on the address numbers, and whether items were removed from the weight sensors.

Systems and methods for carrying out automated inventory control by automatically sensing product levels in-situ, and automatically ordering new product when product levels are determined to be excessively low. Sensor modules may be placed under, over, or near products such as consumer goods, to continuously detect their levels as they are stored in normal use. When detected product levels are sufficiently low, new product can be automatically ordered, or instructions can be transmitted to refill or replace the product. In this manner, product depletion can be detected without user intervention or manual disturbance of the product, and new product can be automatically requested to refill or replace the depleted product.

In some embodiments, a counting machine may include a counting area configured to count a plurality of items. The counting area may include a fixed pressure plate, a movable pressure plate, and one or more sensors configured to measure the distance between the fixed pressure plate and the movable pressure plate, and a processor configured to determine the number of items in the counting area by comparing a sampled thickness value to the thickness of the items located between the fixed pressure plate and the movable pressure plate.

In some embodiments, a counting machine may include a counting area configured to count a plurality of items. The counting area may include a fixed pressure plate, a movable pressure plate, and one or more sensors configured to measure the distance between the fixed pressure plate and the movable pressure plate, and a processor configured to determine the number of items in the counting area by comparing a sampled thickness value to the thickness of the items located between the fixed pressure plate and the movable pressure plate.

A shelf bracket assembly mounted upright on a vertically disposed shelf has: a load cell; an anchor; and a cantilever supporting a shelf panel. The cantilever projects from the shelf upright in a substantially horizontal direction. The cantilever has a vertically disposed frame or a vertically disposed metal plate and a mount for the load cell. The load cell has a monolithic measuring body that has: a force-supporting section; a force-introduction section; and a linkage section between the force-supporting section and the force-introduction section. The force-supporting section of the monolithic measuring body is laterally attached to the mount. The monolithic measuring body has at least one mounting hole through which the monolithic measuring body is attached to the mount with a screw extending horizontally through the monolithic measuring body.