Object detection is a critical component of computer vision, with significant applications across various domains. The challenges associated with real-world images, including noise, blurring, and rotational jitter, substantially impact the performance of object detection algorithms. YOLO (You Only Look Once), an algorithm grounded in convolutional neural networks, offers real-time object detection capabilities. This paper delves into several enhancements made to the YOLO network, aimed at augmenting the precision and efficiency of object detection tasks. The advancements discussed include optimizing the architecture of YOLO to handle diverse environmental conditions and integrating state-of-the-art techniques to mitigate common image distortions. Moreover, the paper explores the application of light field cameras to enhance depth perception and object localization. By refining the YOLO network, we aim to push the boundaries of real-time detection accuracy and reliability, crucial for applications ranging from autonomous vehicles to security surveillance systems.