Enhancing Indoor Object Detection with xLSTM Attention-Driven YOLOv9 for Improved 2D-Driven 3D Object Detection

Three-dimensional (3D) object detection is crucial for applications such as robotic control and autonomous driving. While high-precision sensors like LiDAR are expensive, RGB-D sensors (e.g., Kinect) offer a cost-effective alternative, especially for indoor environments. However, RGB-D sensors still face limitations in accuracy and depth perception. This paper proposes an enhanced method that integrates attention-driven YOLOv9 with xLSTM into the F-ConvNet framework. By improving the precision of 2D bounding boxes generated for 3D object detection, this method addresses issues in indoor environments with complex structures and occlusions. The proposed approach enhances detection accuracy and robustness by combining RGB images and depth data, offering improved indoor 3D object detection performance.