Change detection is an elementary task in computer vision and video processing applications. Recently, a number of supervised methods based on convolutional neural networks have reported high performance over the benchmark dataset. However, their success depends upon the availability of certain proportions of annotated frames from test video during training. Thus, their performance on completely unseen videos or scene independent setup is undocumented in the literature. In this work, we present a scene independent evaluation (SIE) framework to test the supervised methods in completely unseen videos to obtain generalized models for change detection. In addition, a scene dependent evaluation (SDE) is also performed to document the comparative analysis with the existing approaches. We propose a fast (speed-25 fps) and lightweight (0.13 million parameters, model size-1.16 MB) end-to-end 3D-CNN based change detection network (3DCD) with multiple spatiotemporal learning blocks. The proposed 3DCD consists of a gradual reductionist block for background estimation from past temporal history. It also enables motion saliency estimation, multi-schematic feature encoding-decoding, and finally foreground segmentation through several modular blocks. The proposed 3DCD outperforms the existing state-of-the-art approaches evaluated in both SIE and SDE setup over the benchmark CDnet 2014, LASIESTA and SBMI2015 datasets. To the best of our knowledge, this is a first attempt to present results in clearly defined SDE and SIE setups in three change detection datasets.

Glaucoma is an eye disease that damages the optic nerve head (ONH) causing loss of vision. Therefore, early diagnosis and treatment are important in preventing possible blindness caused by glaucoma. Its current identification is based on the manual segmentation of the optic cup and disc to examine the cup-to-disc ratio (CDR). However, experts’ annotation of these regions is a rather difficult and tedious task. Employing a convolutional neural network (CNN) for diagnosing glaucoma could be an alternative solution. However, its performance depends on the availability of a large number of labeled samples for the training phase. This paper presents an automatic glaucoma diagnosing framework based on three convolutional neural network (CNN) models with different learning methods, and compares the performance of these models with ophthalmologists. We use transfer and semi-supervised learning methods based on both labeled and unlabeled data. First, the transfer learning model starts with a pre-trained CNN model that was trained with non-medical data and fine-tunes it with our labeled data. Secondly, a semi-supervised framework is developed and trained using both labeled and unlabeled data based on two different unsupervised methods. The experimental results using two datasets, RIM-ONE and RIGA, demonstrate the efficacy of deep learning models when applied to glaucoma, which is a promising step towards automated screening for identifying individuals with early-stage glaucoma. Compared with annotations by two ophthalmologists, all the presented models achieve better performances, demonstrating the capability of artificial intelligence in diagnosing glaucoma with a high level of reliability.

Advances in deep learning (DL) have triggered an explosion of mobile intelligence, posing a soaring demand for computing resources that cannot be satisfied by mobile devices. In this article, we employ edge computing to deliver better DL inference services to end users. The key is to leverage deep neural network (DNN) ensemble techniques that provide state-of-the-art performance for many machine learning applications in terms of inference accuracy and robustness. Compared to end devices, the edge computing platform is endowed with more powerful computing resources, making it feasible to implement DNN ensembles for DL inferences. However, due to the constrained computing capacity of edge servers and the possible service response deadline, an edge server can only use a limited number of DNNs to construct DNN ensembles. This poses a unique problem, namely, DNN ensemble selection, for identifying the best-fit DNN ensembles. We propose a novel algorithm called automated DNN ensemble selection (AES) algorithm to solve this problem. Because DNNs exhibit performance variations over different distributions of input data, AES adaptively determines a DNN ensemble according to the features of admitted inference tasks. AES is an online learning algorithm that learns DNNs’ in-use performance over time. An ensemble selection rule is further designed as a subroutine of AES to recruit members into the DNN ensemble based on the accuracy and diversity of DNNs. In particular, we theoretically prove that AES can achieve asymptotic optimality. We carry out experiments on real-world data sets. The results show that using the DNN ensemble technique on edge computing platforms dramatically improves the DL inference quality, and AES outperforms other benchmark schemes.