Abstract: A method includes generating a plurality of lidar inputs based on the lidar data, where each lidar input from among the plurality of lidar inputs comprises an image-based portion and a geometric-based portion, and where each lidar input from among the plurality of lidar inputs defines a position coordinate of the one or more objects. The method includes performing, for each lidar input from among the plurality of lidar inputs, a convolutional neural network (CNN) routine based on the image-based portion to generate one or more image-based outputs and assigning the plurality of lidar inputs to a plurality of echo groups based on the geometric-based portion. The method includes concatenating the one or more image-based outputs and the plurality of echo groups to generate a plurality of fused outputs and identifying the one or more objects based on the plurality of fused outputs.

Abstract: A bookshelf saferoom includes a rectangular frame structure, a front panel, a rear panel, a lateral panel, a door panel, a top panel, a bottom panel, at least one locking assembly, and a plurality of shelves. The rectangular frame structure is perimetrically enclosed by the front panel, the rear panel, the lateral panel, the top panel, and the bottom panel to configure an enclosure. The entrance opening is delineated by the front panel, the rear panel, the lateral panel, the top panel, and the bottom panel thus allowing the door panel to be hingedly mounted to the rectangular frame structure. The least one locking assembly is integrated between the rectangular frame structure and the door panel to secure the door panel externally or internally. The plurality of shelves is externally mounted to the front panel so that the enclosure can be inconspicuous to the intruders.