Saeed Muhammad

Dr. Saeed Muhammad

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2022 in Wireless Communications and Mobile Computing
Verified
Journal Article
Open access
PDF file
TQTaimoor Qureshi
Taimoor Qureshi
SMSaeed Muhammad
Saeed Muhammad
KAKamran Ahsan
Kamran Ahsan
AMAshfaq Ahmad Malik
Ashfaq Ahmad Malik
EMEmaduddin Shah Muhammad
Emaduddin Shah Muhammad
NTNasir Touheed
Nasir Touheed
Internet of Things (IoT) is being used in various parts of human life (domestic and commercial) to provide ease in living, safety, increase productivity, monitoring, and resource optimization in various industries. Agriculture is one of them, where IoT and robots are being used before and after the cultivation process, from preparing land for cultivation to supplying them to the consumer market. These domains include crop monitoring, smart irrigation, pest monitoring, and smart pest control, harvesting, and safely supplying them in the consumer market by maintaining the quality and integrity of the final product. Pakistan is an agricultural country, where it stands in terms of advanced agriculture technology. In this review, we discussed the major IoT ecosystem components. What are the most practiced smart agriculture techniques and their benefits and some widely used applications of IoT in agriculture? Through this overview, we are trying to highlight the potential of IoT in agriculture for sustainable food security for Pakistan.

30 November 2021 in IEEE Access
Verified
Journal Article
Open access
AHAnwar Ul Haque
Anwar Ul Haque
SGSayeed Ghani
Sayeed Ghani
SMSaeed Muhammad
Saeed Muhammad
The last 5 to 6 years have seen tremendous progress in automatic image captioning using deep learning. Initial research focused on the attribute-to-attribute comparison of image features and texts to describe the image as a sentence, the current research is handling issues related to semantics and correlations. However, current state of art research suffers from insufficient concepts when it comes to positional and geometrical attributes. The majority of research relying on CNN’s (Convolutional Neural Networks) for object feature extractions has no clue about equivariance and rotational invariance which leads towards the orientation-less understanding of objects for captioning along with longer training time, and larger dataset. Furthermore, CNN’s based image captioning encoders also fail to understand the geometrical alignment of object attributes within the image and hence mislabels distorted as correct. To cater to the above issues, we propose ICPS (Captioning with Positional and geometrical Semantics) a capsule network-based image captioning technique along with transformer neural networks as the decoder. The proposed ICPS architecture handles various geometrical properties of image objects with the help of parallelized capsules while the object-to-text decoding is done by Transformer Neural Networks. The inclusion of cluster capsules provides better object understanding in terms of position, equivariance, and geometrical orientation with more augmented object understanding over a small dataset in comparatively less time. The extracted image features provide a better understanding of image objects and help the decoding stage to narrate effectively with positional and geometrical details. We trained and tested our ICPS over the Flickr8k dataset and found ourselves to be better at captioning when it comes to describing the positional and geometrical transitions as compared to other current state-of-the-art research.

25 June 2025 in IEEE Access
Verified
Journal Article
Open access
KAKumail Abbas
Kumail Abbas
MKM. Imad Khan
M. Imad Khan
SMSaeed Muhammad
Saeed Muhammad
KAKhandakar Ahmed
Khandakar Ahmed
HWHua Wang
Hua Wang
AMArif Mahmood
Arif Mahmood
The use of technology in cricket has seen a significant increase in recent years, leading to overlapping computer vision-based research efforts. This study aims to extract front pitch view shots in cricket broadcasts by utilizing deep learning. The front pitch view (FPV) shots include ball delivery by the bowler and the stroke played by the batter. FPV shots are valuable for highlight generation, automatic commentary generation and bowling and batting techniques analysis. We classify each broadcast video frame as FPV and non-FPV using deep-learning models. We also detect pitch and umpire using recent object detectors. If a frame is classified FPV and pitch and umpire are detectable, it is considered as part of the FPV shot. In each FPV shot, we then track the cricket ball for further analysis using deep-learning-based fast-moving object trackers. Using the ball tracking, we first detect the ball bounce position on the pitch and using that position we classify the FPV video shots as full-pitched, good-length, or short-pitched deliveries. For training and testing purposes, we manually annotated four different datasets: (i) Front Pitch View (FPV) classification dataset consisting of 10k frames including 5k positive and 5k negative frames, (ii) Pitch and Umpire Detection (PUD) dataset consisting of 5k frames with manually annotated pitches and umpires, (iii) Ball Tracking Dataset (BTD) consisting of 3k frames with balls annotated and 6k frames with no visible balls, (iv) Ball Delivery Classification (BDC) dataset consisting of 300 video clips annotated as full-pitched, good-length and short-pitched deliveries. For the FPV and PUD datasets, training and testing splits are marked as 50% each. For the BTD and BDC datasets training and testing splits are marked as 80% and 20%. The results of the proposed framework demonstrates its ability to accurately classify cricket shots into FPV and non-FPV, creating the foundation for large datasets of video shots of ball deliveries and strokes that can be used for further processing and semantic extraction. Our work has the potential to be of great benefit to cricket coaches and players for analyzing ball deliveries in a match. Our trained models and four datasets are online available at our Github page https://www.github.com/KumailAbb/FPVShotDetection.

22 November 2022 in arXiv
Verified
Preprint
Open access
PDF file
KAKumail Abbas
Kumail Abbas
SMSaeed Muhammad
Saeed Muhammad
MKM. Imad Khan
M. Imad Khan
KAKhandakar Ahmed
Khandakar Ahmed
HWHua Wang
Hua Wang
There has been a significant increase in the adoption of technology in cricket recently. This trend has created the problem of duplicate work being done in similar computer vision-based research works. Our research tries to solve one of these problems by segmenting ball deliveries in a cricket broadcast using deep learning models, MobileNet and YOLO, thus enabling researchers to use our work as a dataset for their research. The output from our research can be used by cricket coaches and players to analyze ball deliveries which are played during the match. This paper presents an approach to segment and extract video shots in which only the ball is being delivered. The video shots are a series of continuous frames that make up the whole scene of the video. Object detection models are applied to reach a high level of accuracy in terms of correctly extracting video shots. The proof of concept for building large datasets of video shots for ball deliveries is proposed which paves the way for further processing on those shots for the extraction of semantics. Ball tracking in these video shots is also done using a separate RetinaNet model as a sample of the usefulness of the proposed dataset. The position on the cricket pitch where the ball lands is also extracted by tracking the ball along the y-axis. The video shot is then classified as a full-pitched, good-length or short-pitched delivery.

10 December 2025 in IEEE Access
Verified
Journal Article
Open access
AHAnwar Ul Haque
Anwar Ul Haque
SGSayeed Ghani
Sayeed Ghani
SMSaeed Muhammad
Saeed Muhammad
The human ability to detect, understand, and contextualize objects in the real world has long been a dream for computer scientists, who have sought to replicate this capability in machines. Image captioning with context and content is a significant research problem. In this work, we attempted to develop a storytelling system that can caption images, considering content, context, syntax, and knowledge. Our methodology combines Capsule Networks for image encoding, Knowledge Graphs for content and context awareness, and Transformer Neural Networks for decoding. During feature extraction, spatial, geometrical, and orientational details are extracted using Capsule Networks. The corpus is passed through the Knowledge Graph to equip it with content, context, and semantics. The decoding phase combines the Knowledge Graph and the Transformer Neural Network for knowledge-driven captioning. Our model is trained on MSCOCO, Flickr8k, and Flickr32k, and tested on MSCOCO, Flickr8k, Flickr32k, and Google Images. The results provide good content and context understanding with B4: 49.97, M: 39.14, C: 136.53, and R: 74.61. The usage of adverbs and adjectives within the generated sentence, according to the objects’ geometrical and semantic relationship, is phenomenal. The primary outcome of our research is the generation of autonomous story-type captions for real-world images.

1 January 2019 in Mehran University Research Journal of Engineering and Technology
Verified
Journal Article
Open access
PDF file
SISarwat Iqbal
Sarwat Iqbal
SUSana Ullah
Sana Ullah
KAKamran Ahsan
Kamran Ahsan
SMSaeed Muhammad
Saeed Muhammad
MHMuhammad Azhar Hussain
Muhammad Azhar Hussain
Collection and delivery of laundry is an important process in the laundry business. The laundry businesses have adopted diverse models such as over the counter collection/delivery, online booking etc. The laundries are collected or delivered from customers’ doorstep or from customers’ desired location at a convenient time. In this paper, business process re-engineering concept has been incorporated to improve the collection and delivery process of laundry using RFID (Radio-Frequency Identification) tagging and Automated Laundry Collection Drop Box. The Devil’s Quadrangle has been used as a tool for evaluation. The proposed model will result in reduction in cost, time and improvement in service quality. It ultimately results in customers’ loyalty, economic efficiency and gain of a competitive advantage over competitor. Other advantages for laundry business include automatic collection and delivery, enhanced customer convenience, enhanced flexibility and industry economic savings, enhanced customer satisfaction and decreased labor work. In the proposed automated laundry collection model, reputed laundry businesses will make a consortium and outsource collection and delivery process to a courier company. Different collection and delivery options are proposed in the model.