Three Applications of Deep Learning Algorithms for Object Detection in Satellite Imagery

Deep learning (DL) convolutional neural networks (CNNs) have been rapidly adapted in very high spatial resolution (VHSR) satellite image analysis. DLCNN-based computer visions (CV) applications primarily aim for everyday object detection from standard red, green, blue (RGB) imagery, while earth science remote sensing applications focus on geo object detection and classification from multispectral (MS) imagery. MS imagery includes RGB and narrow spectral channels from near- and/or middle-infrared regions of reflectance spectra. The central objective of this exploratory study is to understand to what degree MS band statistics govern DLCNN model predictions. We scaffold our analysis on a case study that uses Arctic tundra permafrost landform features called ice-wedge polygons (IWPs) as candidate geo objects. We choose Mask RCNN as the DLCNN architecture to detect IWPs from eight-band Worldview-02 VHSR satellite imagery. A systematic experiment was designed to understand the impact on choosing the optimal three-band combination in model prediction. We tasked five cohorts of three-band combinations coupled with statistical measures to gauge the spectral variability of input MS bands. The candidate scenes produced high model detection accuracies for the F1 score, ranging between 0.89 to 0.95, for two different band combinations (coastal blue, blue, green (1,2,3) and green, yellow, red (3,4,5)). The mapping workflow discerned the IWPs by exhibiting low random and systematic error in the order of 0.17–0.19 and 0.20–0.21, respectively, for band combinations (1,2,3). Results suggest that the prediction accuracy of the Mask-RCNN model is significantly influenced by the input MS bands. Overall, our findings accentuate the importance of considering the image statistics of input MS bands and careful selection of optimal bands for DLCNN predictions when DLCNN architectures are restricted to three spectral channels.

Download Full-text

Object Detection in High resolution using Satellite Imagery with Deep Learning

International Journal of Scientific Research in Science and Technology ◽

10.32628/ijsrset218258 ◽

2021 ◽

pp. 208-215

Author(s):

Niharika Goswami ◽

Keyurkumar Kathiriya ◽

Santosh Yadav ◽

Janki Bhatt Bhatt ◽

Sheshang Degadwala

Keyword(s):

Deep Learning ◽

High Resolution ◽

Lung Injury ◽

Object Detection ◽

Satellite Imagery ◽

Social Affair ◽

The World ◽

Primary Driver ◽

Onset Period ◽

Basic Learning

Earlier, the progression of the descending lung was the primary driver of the chaos that runs across the world between the two people, with more than a million people dies per year goes by. The cellular breakdown in the lungs has been greatly transferred to the inconvenience that people have looked at for a very predictable amount of time. When an entity suffers a lung injury, they have erratic cells that clump together to form a cyst. A dangerous tumor is a social affair involving terrifying, enhanced cells that can interfere with and strike tissue near them. The area of lung injury in the onset period became necessary. As of now, various systems that undergo a preparedness profile and basic learning methodologies are used for lung risk imaging. For this, CT canal images are used to see and save the adverse lung improvement season from these handles. In this paper, we present an unambiguous method for seeing lung patients in a painful stage. We have considered the shape and surface features of CT channel pictures for the sales. The perspective is done using undeniable learning methodologies and took a gender at their outcome.

Download Full-text

Trajectory Object Detection using Deep Learning Algorithms

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.c6564.098319 ◽

2019 ◽

Vol 8 (3) ◽

pp. 7895-7898

Keyword(s):

Deep Learning ◽

Object Detection ◽

Large Scale ◽

Smart Cities ◽

Learning Algorithms ◽

Big Data Analytics ◽

Light Condition ◽

Transport Systems ◽

Video Footage ◽

Vehicle Type

Video surveillance data in smart cities needs to analyze a large amount of video footage in order to locate the people who are violating the traffic rules. The fact is that it is very easy for the human being to recognize different objects in images and videos. For a computer program this is quite a difficult task. Hence there is a need for visual big data analytics which involves processing and analyzing large scale visual data such as images or videos. One major application of trajectory object detection is the Intelligent Transport Systems (ITS). Vehicle type detection, tracking and classification play an important role in ITS. In order to analyze huge amount of video footage deep learning algorithms have been deployed. The main phase of vehicle type detection includes annotating the data, training the model and validating the model. The problems and challenges in identifying or detecting type of vehicle are due to weather, shadows, blurring effect, light condition and quality of the data. In this paper deep learning algorithms such as Faster R CNN and Mask R CNN and Frameworks like YOLO were used for the object detection. Dataset (different types of vehicle pictures in video format) were collected both from in-house premises as well as from the Internet to detect and recognize the type of vehicles which are common in traffic systems. The experimental results show that among the three approaches used the Mask R CNN algorithm is found to be more efficient and accurate in vehicle type detection.

Download Full-text

Medicine Delivery Bot Using Time Series and Object Detection

International Journal of Scientific Research in Science and Technology ◽

10.32628/cseit217469 ◽

2021 ◽

pp. 286-290

Author(s):

Kartikeya Bajpai ◽

Prachi Jain

Keyword(s):

Time Series ◽

Deep Learning ◽

Object Detection ◽

Learning Algorithms ◽

Research Paper ◽

Traffic Light ◽

Lapse Time ◽

Manual Work ◽

Traffic Lights ◽

Present Context

Nowadays, delivery is mainly done by humans which includes a lot of manual work. The existing way is good but lacks faster deliveries. In the present context the deliveries are not possible 24*7 by humans, especially in the case of medicines, customers often require immediate deliveries for maintaining their course of medication. Since, in many other fields AI has contributed to decreasing a lot of manual work and time. In this research paper, we have proposed the idea of a delivery bot which uses deep learning algorithms to detect traffic lights and classify the color of the traffic light. On the basis of which the lapse time will be calculated in between the two traffic lights and hence maps the route for delivery with the help of geocoding accordingly which helps in more secure and faster deliveries.

Download Full-text

DiaMole: Mole Detection and Segmentation Software for Mobile Phone Skin Images

Journal of Healthcare Engineering ◽

10.1155/2021/6698176 ◽

2021 ◽

Vol 2021 ◽

pp. 1-10

Author(s):

Shuai Liu ◽

Zheng Chen ◽

Huahui Zhou ◽

Kunlin He ◽

Meiyu Duan ◽

...

Keyword(s):

Deep Learning ◽

Object Detection ◽

Mobile Phone ◽

Early Stage ◽

Learning Algorithms ◽

Skin Lesions ◽

Detection Algorithm ◽

Incidence And Mortality ◽

Malignant Skin ◽

User Friendly

Motivation. The worldwide incidence and mortality rates of melanoma are on the rise recently. Melanoma may develop from benign lesions like skin moles. Easy-to-use mole detection software will help find the malignant skin lesions at the early stage. Results. This study developed mole detection and segmentation software DiaMole using mobile phone images. DiaMole utilized multiple deep learning algorithms for the object detection problem and mole segmentation problem. An object detection algorithm generated a rectangle tightly surrounding a mole in the mobile phone image. Moreover, the segmentation algorithm detected the precise boundary of that mole. Three deep learning algorithms were evaluated for their object detection performance. The popular performance metric mean average precision (mAP) was used to evaluate the algorithms. Among the utilized algorithms, the Faster R-CNN could achieve the best mAP = 0.835, and the integrated algorithm could achieve the mAP = 0.4228. Although the integrated algorithm could not achieve the best mAP, it can avoid the missing of detecting the moles. A popular Unet model was utilized to find the precise mole boundary. Clinical users may annotate the detected moles based on their experiences. Conclusions. DiaMole is user-friendly software for researchers focusing on skin lesions. DiaMole may automatically detect and segment the moles from the mobile phone skin images. The users may also annotate each candidate mole according to their own experiences. The automatically calculated mole image masks and the annotations may be saved for further investigations.

Download Full-text

Satellite Imagery Classification with Deep Learning : A Survey

International Journal of Scientific Research in Computer Science Engineering and Information Technology ◽

10.32628/cseit2065124 ◽

2020 ◽

pp. 36-46

Author(s):

Niharika Goswami ◽

Keyurkumar Kathiriya ◽

Santosh Yadav ◽

Janki Bhatt ◽

Sheshang Degadwala

Keyword(s):

Deep Learning ◽

High Resolution ◽

Object Detection ◽

Satellite Imagery ◽

Satellite Images ◽

Weather Forecasting ◽

Vehicle Detection ◽

Suitable Alternative ◽

High Resolution Satellite Images ◽

Technological Developments

Object detection from satellite images has been a challenging problem for many years. With the development of effective deep learning algorithms and advancement in hardware systems, higher accuracies have been achieved in the detection of various objects from very high-resolution satellite images. In the past decades satellite imagery has been used successfully for weather forecasting, geographical and geological applications. Low resolution satellite images are sufficient for these sorts of applications. But the technological developments in the field of satellite imaging provide high resolution sensors which expands its field of application. Thus, the High-Resolution Satellite Imagery (HRSI) proved to be a suitable alternative to aerial photogrammetric data to provide a new data source for object detection. Since the traffic rates in developing countries are enormously increasing, vehicle detection from satellite data will be a better choice for automating such systems. In this research, a different technique for vehicle detection from the images obtained from high resolution sensors is reviewed. This review presents the recent progress in the field of object detection from satellite imagery using deep learning.

Download Full-text