A comparison of deep learning models for end-to-end face-based video retrieval in unconstrained videos

Face-based video retrieval (FBVR) is the task of retrieving videos that containing the same face shown in the query image. In this article, we present the first end-to-end FBVR pipeline that is able to operate on large datasets of unconstrained, multi-shot, multi-person videos. We adapt an existing audiovisual recognition dataset to the task of FBVR and use it to evaluate our proposed pipeline. We compare a number of deep learning models for shot detection, face detection, and face feature extraction as part of our pipeline on a validation dataset made of more than 4000 videos. We obtain 97.25% mean average precision on an independent test set, composed of more than 1000 videos. The pipeline is able to extract features from videos at $$\sim $$ ∼ 7 times the real-time speed, and it is able to perform a query on thousands of videos in less than 0.5 s.

Temporal Video Segmentation Using Optical Flow Estimation

Shot boundary detection is the process of segmenting a video into basic units known as shots by discovering transition frames between shots. Researches have been conducted to accurately detect the shot boundaries. However, the acceleration of the shot detection process with higher accuracy needs improvement. A new method was introduced in this paper to find out the boundaries of abrupt shots in the video with high accuracy and lower computational cost. The proposed method consists of two stages. First, projection features were used to distinguish non boundary transitions and candidate transitions that may contain abrupt boundary. Only candidate transitions were conserved for next stage. Thus, the speed of shot detection was improved by reducing the detection scope. In the second stage, the candidate segments were refined using motion feature derived from the optical flow to remove non boundary frames. The results manifest that the proposed method achieved excellent detection accuracy (0.98 according to F-Score) and effectively speeded up detection process. In addition, the comparative analysis results confirmed the superior performance of the proposed method versus other methods.

Artificial Intelligence System for Effective Detection of Animal Intervention in Croplands

Animal intervention is significant intimidation to the potency of the crops, which influences food security and decreases the value to the farmers. This suggested model displays the growth of the Internet of Things and Machine learning technique-based resolutions to surmount this obstacle. Raspberry Pi commands the machine algorithm, which is interfaced with the ESP8266 Wireless Fidelity module, Pi-Camera, Speaker/Buzzer, and LED. Machine learning algorithms similar to Regionbased Convolutional Neural Network and Single Shot Detection technology represents an essential function to identify the target in the pictures and classify the creatures. The experimentation exhibits that the Single Shot Detection algorithm exceeds than Region-based Convolutional Neural Network algorithm. Ultimately, the Twilio API interfaced software decimates the data to the farmers to take conclusive work in their farm territory. Keywords: Region-Based Convolutional Neural Network (R-CNN), Tensor Flow, Raspberry Pi, Internet of Things (IoT), Single Shot Detector (SSD)

Few-Shot Object Detection on Remote Sensing Images via Shared Attention Module and Balanced Fine-Tuning Strategy

Few-shot object detection is a recently emerging branch in the field of computer vision. Recent research studies have proposed several effective methods for object detection with few samples. However, their performances are limited when applied to remote sensing images. In this article, we specifically analyze the characteristics of remote sensing images and propose a few-shot fine-tuning network with a shared attention module (SAM) to adapt to detecting remote sensing objects, which have large size variations. In our SAM, multi-attention maps are computed in the base training stage and shared with the feature extractor in the few-shot fine-tuning stage as prior knowledge to help better locate novel class objects with few samples. Moreover, we design a new few-shot fine-tuning stage with a balanced fine-tuning strategy (BFS), which helps in mitigating the severe imbalance between the number of novel class samples and base class samples caused by the few-shot settings to improve the classification accuracy. We have conducted experiments on two remote sensing datasets (NWPU VHR-10 and DIOR), and the excellent results demonstrate that our method makes full use of the advantages of few-shot learning and the characteristics of remote sensing images to enhance the few-shot detection performance.

Detecting Facial Region and Landmarks at Once via Deep Network

For accurate and fast detection of facial landmarks, we propose a new facial landmark detection method. Previous facial landmark detection models generally perform a face detection step before landmark detection. This greatly affects landmark detection performance depending on which face detection model is used. Therefore, we propose a model that can simultaneously detect a face region and a landmark without performing the face detection step before landmark detection. The proposed single-shot detection model is based on the framework of YOLOv3, a one-stage object detection method, and the loss function and structure are altered to learn faces and landmarks at the same time. In addition, EfficientNet-B0 was utilized as the backbone network to increase processing speed and accuracy. The learned database used 300W-LP with 64 facial landmarks. The average normalized error of the proposed model was 2.32 pixels. The processing time per frame was about 15 milliseconds, and the average precision of face detection was about 99%. As a result of the evaluation, it was confirmed that the single-shot detection model has better performance and speed than the previous methods. In addition, as a result of using the COFW database, which has 29 landmarks instead of 64 to verify the proposed method, the average normalization error was 2.56 pixels, which was also confirmed to show promising performance.

Wireless Speed Control of Vehicles with Detection of Person & Zebra Crossing

Pedestrians crossing zebra lines are one of the major concerns for road accidents. Nowadays, the number of road accidents increases due to careless driving and pedestrian motions at crosswalks. It is necessary to detect both person and zebra crossings properly and control vehicle speed accordingly. Here in this paper, a suitable solution that improves both detections can be introducing. Here used the TensorFlow Single Shot Detection (SSD) model is the best and most convenient trained model for Zebra line and person detection. A database is taking for the analysis. The input image could process as a crosswalk detection, which has more used for zebra crossing identification via the SSD model. Suppose detected the person and zebra crossings were at the same time. In that case, it will perform commands such as run, slow down, stop, horn, etc., with the help of wireless serial communication Universal Asynchronous Receiver-Transmitter. A Bluetooth command signal matches UART, which provides the vehicle with the necessary control inputs to execute the prescribed topology properly. Simultaneous detection of pedestrians at zebra crossings is a critical factor. It results most efficiently and to identify the person detection.