Muhammad Umraiz

Papers

Total Citations

H-Index

About

Muhammad Umraiz is a researcher whose work sits at the intersection of computer vision, precision agriculture, and autonomous robotics. His primary contributions focus on developing deep learning architectures for real-time crop segmentation, a critical step toward enabling fully autonomous harvesting systems. In his highly cited 2021 paper, "DAM: Hierarchical Adaptive Feature Selection Using Convolution Encoder Decoder Network for Strawberry Segmentation" (23 citations), Umraiz tackled the formidable challenge of segmenting strawberries in unstructured, occluded farm environments. He introduced a novel hierarchical feature selection mechanism integrated with a convolutional encoder-decoder network, significantly improving the model's ability to distinguish ripe fruit from complex backgrounds—a task that has long stymied agricultural robots. This work directly addresses the practical need for reliable, real-time visual perception in high-value crop cultivation, particularly for strawberries. By advancing adaptive feature selection, Umraiz has contributed a foundational technique that enhances the robustness of segmentation models under variable lighting, overlapping foliage, and fruit occlusion. His research holds clear promise for reducing labor costs and improving harvest timeliness, marking him as a key contributor to the growing field of intelligent agricultural automation.