Object detection device and method

An object detection device, comprising:

• an image-extraction device, extracting a plurality of images and a plurality of depth images in a specific space, wherein each image corresponds to one of the plurality of depth images;
• and
• a processor, coupled to the image-extraction device, and obtaining the plurality of images and the plurality of depth images from the image-extraction device,
• wherein the processor detects objects in each image using an object detection model to obtain object information,
• wherein the processor calculates depth value of each object in each depth image,
• wherein the processor inputs the depth value of each object into an object status model to determine object status of each object,
• wherein the object detection device, via the processor, determines whether to enter the specific space based on the object information and the object status of each object,
• wherein the processor determines whether the objects comprise at least one specific object based on the object information, wherein the specific object is wheelchair, stroller or cart,
• wherein in response to the objects comprising the at least one specific object, the processor indicates the object detection device to move back, and determines whether the specific object leaves the specific space based on the object status of the specific object, and
• wherein in response to the specific object not leaving the specific space, the object detection device, via the processor, determines not to enter the specific space.