An imaging system capture images of products on shelves in a minimally invasive way. The images can be processed to assess restocking needs and other information. The imaging system includes multiple shelf-mountable imaging devices that can be positioned throughout one or more retail locations. Certain types of imaging devices may be self-contained units having replaceable or rechargeable internal power sources and/or wireless communication interfaces. Certain types of imaging device are configured to take images only when the field of view is not blocked by traffic (e.g., consumers, employees, etc.). Certain types of imaging devices are low-profile and/or are camouflageable to enhance the user experience.

A shelving assembly is provided for a container. The shelving assembly includes a first shelf movably positioned in the container and configured to support a first stock. The shelving assembly further includes a plurality of first support members configured to support the first shelf and displace the first shelf between a first position and a second position in the container based on a weight sensed by at least one first weight sensor to maintain the first stock at an opening of the container. Additionally, the shelving assembly includes a second shelf positioned adjacent within the container and configured to support a second stock. The first shelf is configured to be removed at the second position to facilitate the first stock descending onto the second stock on the second shelf. Accordingly, the shelving assembly facilitates first in first out stock rotation.

Systems and techniques are provided for determining an improved camera coverage plan including a number, a placement, and a pose of cameras that are arranged to track puts and takes of items by subjects in a three-dimensional real space. The method includes receiving an initial camera coverage plan including a three-dimensional map of a real space, an initial number and initial pose of a plurality of cameras and a camera model including characteristics of the cameras. The method can iteratively apply a machine learning process to an objective function of number and poses of cameras, and subject to a set of constraints, obtain an improved camera coverage plan. The improved camera coverage plan is provided to an installer to arrange cameras to track puts and takes of items by subjects in the three-dimensional real space.

Systems, apparatuses, and methods for determining item availability are provided. A computer implemented method for determining item availability in a shopping space comprising: receiving a request for an item for purchase from a customer, querying an inventory database to determine whether the item for purchase is in stock, in an event that the item for purchase is not in stock according to the inventory database: determining an out of stock response to present to the customer, in an event that the item for purchase is in stock according the inventory database: instructing a motorized transport unit to travel to a display space in the shopping space corresponding to the item for the purchase, determining whether the item is available in the display space based on information captured by one or more sensors of the motorized transport unit, and in an event that the item for purchase is not available in the display space: determining an item unavailable response to present to the customer.

Disclosed is a system for real-time measurement of inventory on shelves. The system uses light sensors placed in association with the inventory and the shelves to measure in real-time the removal/replacement of inventory from the shelves. When inventory is on the shelves, less light reaches the light sensors. As inventory is removed from shelves, the light sensors receive more light. The difference in light received generates as signal that can be measured, thereby allowing for determining inventory levels on each shelf. The system may be retro-fitted to existing shelving systems, thereby avoiding the cost of purchasing new shelving systems. The system can work on any shelving system, including gravity-feed roller shelf (GRS), flat shelves, and spring loaded pusher shelves, and is unaffected by usual temperatures found in retail establishments and can thus work in both refrigerated and unrefrigerated systems. Also disclosed are related methods.

Embodiments of this disclosure provide a goods shelf system and a method of monitoring items of the goods shelf system. The goods shelf system comprises: a goods shelf comprising a bearing body for bearing an item; a signal transmitting unit located on a side of the bearing body; a plurality of signal receiving units, located on the bearing body, for receiving a signal transmitted by the signal transmitting unit; and a processing unit, electrically connected with the signal receiving unit, for acquiring a storage state of the item on the bearing body according to an signal outputted by the signal receiving unit, wherein one or more of the plurality of signal receiving units shielded by the items are not able to receive the signal transmitted by the signal transmitting unit.

Systems, computer-readable instructions, and methods for storing products are disclosed. For example, the system may include modular shelving units that include a shelf which is placeable on a rack, the shelf including a platform, the shelf having a weight sensor below the platform, the platform is configured to support N number of holders, each of the N holders configured to store products, each shelf further having N−1 optical sensors below the N−1 holders when the N−1 holders are supported by the platform and N−1 windows above the N−1 optical sensors, the N−1 optical sensors being in proximity of the N−1 holders, respectively, wherein each holder includes an opening, wherein when a holder is on the shelf, the opening is capable of being aligned with an optical sensor, the shelf further having a processing circuit coupled to the N−1 optical sensors and the weight sensor.

Systems and techniques are provided for determining an improved camera coverage plan including a number, a placement, and a pose of cameras that are arranged to track puts and takes of items by subjects in a three-dimensional real space. The method includes receiving an initial camera coverage plan including a three-dimensional map of a real space, an initial number and initial pose of a plurality of cameras and a camera model including characteristics of the cameras. The method can iteratively apply a machine learning process to an objective function of number and poses of cameras, and subject to a set of constraints, obtain an improved camera coverage plan. The improved camera coverage plan is provided to an installer to arrange cameras to track puts and takes of items by subjects in the three-dimensional real space.

A merchandise dispensing apparatus for deterring theft has at least one merchandise support module which includes a covering defining an interior space within the module. A support member and a dispensing member are mounted to the module, the dispensing member being mounted adjacent to the support member. A lockout device is also mounted to each module and connected to the dispensing member. The lockout device includes a housing with a user input member accessible from outside the housing. The user input member communicates with the dispensing member. A controller, which includes a memory and a processor, electrically communicates with the user input member. A sensor electrically communicates with the controller and senses the dispensing of an associated packaged item mounted on the support member. A signaling device electrically communicates with the controller to provide a notification upon the dispensing of the associated packaged item.

A modular inventory management system is disclosed herein that includes a bin module. The bin module may include a module base, a sensor configuration, and a divider. The module base may have a first lateral edge, a second lateral edge, and a top surface that connects the first lateral edge to the second lateral edge. The sensor configuration may be arranged on the module base between the first lateral edge and the second lateral edge. The sensor configuration may include a plurality of sensor elements that are arranged in a single row on a center axis of the module base and configured to sense whether one or more objects are positioned on the top surface of the module base. The divider may be situated at the first lateral edge and may be configured to slide laterally with respect to the module base to adjust a width of the bin module.