Traditional Compression Techniques Research Articles

Semantic-Aware Video Compression for Automotive Cameras

Assisted and automated driving functions in vehicles exploit sensor data to build situational awareness, however, the data amount required by these functions might exceed the bandwidth of current wired vehicle communication networks. Consequently, sensor data reduction, and automotive camera video compression need investigation. However, conventional video compression schemes, such as H.264 and H.265, have been mainly optimised for human vision. In this paper, we propose a semantic-aware (SA) video compression (SAC) framework that compresses separately and simultaneously region-of-interest and region-out-of-interest of automotive camera video frames, before transmitting them to processing unit(s), where the data are used for perception tasks, such as object detection, semantic segmentation, etc. Using our newly proposed technique, the region-of-interest (ROI), encapsulating most of the road stakeholders, retains higher quality using lower compression ratio. The experimental results show that under the same overall compression ratio, our proposed SAC scheme maintains a similar or better image quality, measured accordingly to traditional metrics and to our newly proposed semantic-aware metrics. The newly proposed metrics, namely SA-PSNR, SA-SSIM, and iIoU, give more emphasis to ROI quality, which has an immediate impact on the planning and decisions of assisted and automated driving functions. Using our SA-X264 compression, SA-PSNR and SA-SSIM have an increase of 2.864 and 0.008 respectively compared to traditional H.264, with higher ROI quality and the same compression ratio. Finally, a segmentation-based perception algorithm has been used to compare reconstructed frames, demonstrating a 2.7% mIOU improvement, when using the proposed SAC method versus traditional compression techniques.

PTcomp: Post-Training Compression Technique for Generative Adversarial Networks

In a time of virtual spaces, the usage of generative adversarial networks is inevitable. Generative adversarial networks (GANs) are generative deep-learning models that can generate realistic data. GANs have been used in many applications like text-to-image, image-to-image, image synthesis, speech synthesis, etc. Its power lies in the diversity and novelty of the generated data. Despite their advantages, GANs are resource-hungry. GANs’ output resolution and high correlation make it more challenging to compress and fit on edge-devices storage and power budget. Hence, traditional compression techniques are not the best fit to use with GANs. Additionally, GANs training instability adds another dimension of difficulty. Therefore, compression techniques that require retraining are challenging for GANs. In this paper, we developed a weight clustering technique to compress GANs without the need for retraining, hence the name post-training compression technique (PTcomp). We also proposed a clustered-based pruning which adds more savings. Experiments on Cyclegan, Deep convolution gan (DCGAN), and Stargan using several datasets show the superiority of our technique against traditional post-training quantization. Our technique provides a 4x to 8x compression ratio with comparable quality to original models and 14% fewer mac operations due to pruning.

Fuzzy Adaptive-Sampling Block Compressed Sensing for Wireless Multimedia Sensor Networks.

The transmission of high-volume multimedia content (e.g., images) is challenging for a resource-constrained wireless multimedia sensor network (WMSN) due to energy consumption requirements. Redundant image information can be compressed using traditional compression techniques at the cost of considerable energy consumption. Fortunately, compressed sensing (CS) has been introduced as a low-complexity coding scheme for WMSNs. However, the storage and processing of CS-generated images and measurement matrices require substantial memory. Block compressed sensing (BCS) can mitigate this problem. Nevertheless, allocating a fixed sampling to all blocks is impractical since each block holds different information. Although solutions such as adaptive block compressed sensing (ABCS) exist, they lack robustness across various types of images. As a solution, we propose a holistic WMSN architecture for image transmission that performs well on diverse images by leveraging saliency and standard deviation features. A fuzzy logic system (FLS) is then used to determine the appropriate features when allocating the sampling, and each corresponding block is resized using CS. The combined FLS and BCS algorithms are implemented with smoothed projected Landweber (SPL) reconstruction to determine the convergence speed. The experiments confirm the promising performance of the proposed algorithm compared with that of conventional and state-of-the-art algorithms.

Optimal Compression of Medical Images

In today’s healthcare system, medical images are playing a vital role in the diagnosis. The challenges arise to the hospital management systems (HMS) are to store and communicate the large volume of medical images generated by various imaging modalities. Efficient compression of medical images is required to reduce the bit rate to increase the storage capacity and speed-up the transmission without affecting its quality. Over the past few decades, several compression standards have been proposed. In this paper, an intelligent JPEG2000 compression scheme is presented to compress the medical images efficiently. Unlike the traditional compression techniques, genetic programming (GP)-based quantization matrices are used to quantize the wavelet coefficients of the input image. Experimental results validate the usefulness of the proposed intelligent compression scheme.

Comparative study on the in vitro performance of blister molded and conventional lornoxicam immediate release liquitablets: accelerated stability study and anti-inflammatory and ulcerogenic effects

Context: Lornoxicam is a potent non-steroidal anti-inflammatory drug (NSAID). It shows limited solubility in the gastric pH, delayed bioavailability and pharmacodynamic effects with aggravated gastric side effects (due to longer residence in the stomach wall).Objective: To enhance dissolution of lornoxicam in the gastric fluid and expectedly absorption and pharmacological action, with less ulcerogenic effects.Materials and methods: Formulation of immediate release (IR) lornoxicam liquitablets containing both liquid and solid release modulators (wetting agent, solubilizers and microenvironmental pH modifiers). Beside the traditional direct compression technique employed for the preparation of liquitablets a new technique, blister molding, was also used. The effect of the two different manufacturing methods on the fast release characteristics (rapid disintegration and dissolution) was studied. Stability and pharmacological activity of the optimum formula were also explored.Results: Similarity factor pointed out the superiority of molding technique in enhancing dissolution of lornoxicam owing to significant crystallinity reduction (XRD). Optimum formula showed negligible change in drug content and dissolution profiles over 12 weeks, significantly improved anti-inflammatory activity and significantly reduced gastric ulcerative effect over pure lornoxicam and commercial formula.Discussion and conclusion: Blister molded lornoxicam liquitablet of improved dissolution and pharmacological activity and less gastric erosion was successfully prepared.

Lossy compression of satellite images with low impact on vegetation features

A novel technique for lossy compression of satellite images aiming at decreasing the impact on vegetation features is presented in this paper. First, the satellite image bands are divided into two groups; the first group contains the most significant bands for vegetation feature extraction (i.e., vegetation group), and the other contains the rest of the spectral bands. After that, a new band ordering algorithm is applied that improves compression performance. The proposed compression technique is based on a new rate control scheme in which the vegetation group is encoded at a higher bit rate than that for the remaining group. We have selected two of the most common indices to assess the impact of lossy compression on the vegetation features in the satellite images; the Normalized Difference Vegetation Index and the Normalized Difference Water Index. The study is performed on several satellite images, where multispectral images are selected from a Landsat ETM $$+$$ satellite, and hyperspectral images are selected from an Airborne Visible/Infrared Imaging Spectrometer satellite. The experimental results show that the proposed technique is more effective than other traditional compression techniques.

Automatic detection of absence seizures with compressive sensing EEG

Absence epilepsy, a neurological disorder, is characterized by the recurrence of seizures, which have serious impact on the sufferers׳ daily life. The seizure detection has a great importance in the diagnosis and therapy of epileptic patients. Visual inspection of the electroencephalogram (EEG) signals for detection of interictal, pre-ictal and ictal activities is a strenuous and time-consuming task due to the huge volumes of EEG segments that have to be studied. In this study, we proposed a novel automatic detection method based on the altered compressibility of EEG during the three states with compressive sensing. To evaluate the proposed method, segments of interictal, pre-ictal and ictal EEG segments (100 segments in each state) were used. Two entropies, namely the Sample Entropy (SE) and the permutation Entropy (PE), and Hurst Index (HI) were extracted respectively from the segments to compare with the proposed method. Significant features were selected using the ANOVA test. After evaluating the performance of the selected features by four classifiers (Decision Tree, K-Nearest Neighbor, Discriminant Analysis, Support Vector Machine) respectively, the results show that the proposed method can achieve the highest accuracy of 76.7%, which is higher than HI (55.3%), sample entropy (71%), and permutation entropy (73%). Hence, the altered compressibility of EEG with CS can act as a good biomarker for distinguish seizure-free, per-seizure and seizure state. In addition, compressive sensing requires less energy but has competitive compression ratio compared to traditional compression techniques, which enables our method to tele-monitoring of epilepsy patients using wireless body-area networks in personalized medicine.

Mechanical properties of bulk single crystalline nanoporous gold investigated by millimetre-scale tension and compression testing

In this work, the mechanical behaviour of millimetre-scale, bulk single crystalline, nanoporous gold at room temperature is reported for the first time. Tension and compression tests were performed with a custom-designed test system that accommodates small-scale samples. The absence of grain boundaries in the specimens allowed measurement of the inherent strength of millimetre-scale nanoporous gold in tension. The elastic modulus and strength values in tension and compression were found to be significantly lower than values measured with nanoindentation-based techniques and previously reported in the literature, but close to those reported for millimetre-scale polycrystalline samples tested using traditional compression techniques. Fracture toughness was found to be very low, in agreement with the macroscopic brittleness of nanoporous gold, but this is due to the localization of deformation to a narrow zone of ligaments, which individually exhibit significant plasticity and necking.

Color video compression using color mapping into textured grayscale video frames

Color video compression has become a necessity in the advent of newer applications of color video and its increasing size for higher definitions. New approaches are used to achieve more compression over the traditional and standard compression techniques. Considerable progress has been made of color transfer-based compression techniques that do not modify standard encoders but add some pre-processing and post-processing steps. We present a novel, simple yet robust, color transfer-based compression technique that can be integrated with the standard encoders like MPEG-2, H.264/AVC, etc. We achieve the compression by discarding the color components from all frames in a video sequence except those of the Intra (I) frames. The colored intra frames are converted to gray-textured images. The method is developed based on embedding the colors of the intra frames to low visibility high frequency textures of its gray luminance image. This is achieved by decomposing the luminance of the intra frame using the non-decimated DWT or discrete wavelet frame transform and replacing the bandpass subbands by the chrominance signals. The lowpass band is same as that of the luminance signal. At the output of the decoder, the colored intra frames are recovered using the wavelet transform. Instead of calculating motion vectors, we identify and reuse the motion vectors present in the decoder. The remaining luminance frames of the video are colored with the help of identified motion vectors and the color information of the preceding frames. The proposed codec considerably improves the compression ratio achievable by the standard codec, at the cost of slight increase in computation time at the decoder end.

Near-lossless semantic video summarization and its applications to video analysis

The ever increasing volume of video content on the Web has created profound challenges for developing efficient indexing and search techniques to manage video data. Conventional techniques such as video compression and summarization strive for the two commonly conflicting goals of low storage and high visual and semantic fidelity. With the goal of balancing both video compression and summarization, this article presents a novel approach, called Near-Lossless Semantic Summarization (NLSS), to summarize a video stream with the least high-level semantic information loss by using an extremely small piece of metadata. The summary consists of compressed image and audio streams, as well as the metadata for temporal structure and motion information. Although at a very low compression rate (around 1/40 of H.264 baseline, where traditional compression techniques can hardly preserve an acceptable visual fidelity), the proposed NLSS still can be applied to many video-oriented tasks, such as visualization, indexing and browsing, duplicate detection, concept detection, and so on. We evaluate the NLSS on TRECVID and other video collections, and demonstrate that it is a powerful tool for significantly reducing storage consumption, while keeping high-level semantic fidelity.

Computationally efficient simulation of extracellular recordings with multielectrode arrays

In this paper we present a novel, computationally and memory efficient way of modeling the spatial dependency of measured spike waveforms in extracellular recordings of neuronal activity. We use compartment models to simulate action potentials in neurons and then apply linear source approximation to calculate the resulting extracellular spike waveform on a three dimensional grid of measurement points surrounding the neurons. We then apply traditional compression techniques and polynomial fitting to obtain a compact mathematical description of the spatial dependency of the spike waveform. We show how the compressed models can be used to efficiently calculate the spike waveform from a neuron in a large set of measurement points simultaneously and how the same procedure can be inversed to calculate the spike waveforms from a large set of neurons at a single electrode position. The compressed models have been implemented into an object oriented simulation tool that allows the simulation of multielectrode recordings that capture the variations in spike waveforms that are expected to arise between the different recording channels. The computational simplicity of our approach allows the simulation of a multi-channel recording of signals from large populations of neurons while simulating the activity of every neuron with a high level of detail. We have validated our compressed models against the original data obtained from the compartment models and we have shown, by example, how the simulation approach presented here can be used to quantify the performance in spike sorting as a function of electrode position.

Compression and smart coding of offset and gain maps for intraoral digital x‐ray sensors

The response of indirect x-ray digital imaging sensors is often not homogenous on the entire surface area. In this case, calibration is needed to build offset and gain maps, which are used to correct the sensor output. The sensors of new generation are equipped with an on-board memory, which serves to store these maps. However, because of its limited dimension, the maps have to be compressed before saving them. This step is critical because of the extremely high compression rate required. The authors propose here a novel method to achieve such a high compression rate, without degrading the quality of the sensor output. It is based on quad tree decomposition, which performs an adaptive sampling of the offset and gain maps, matched with a RBF-based interpolation strategy. The method was tested on a typical intraoral radiographic sensor and compared with traditional compression techniques. Qualitative and quantitative results show that the method achieves a higher compression rate and produces images of superior quality. The method can be adopted also in different fields where a high compression rate is required.

Conjugation-based compression for Hebrew texts

Traditional compression techniques do not look deeply into the morphology of languages. This can be less critical in languages like English where most of the sequences are illegal according to the grammatical rules of the language, for example, zx, bv or qe; hence the morphology can add a little information that can be beneficial for the compression algorithm. However, this negligence can be a significant flaw in languages like Hebrew where the grammatical rules allow much more freedom in the sequences of letters and, except tet after gimel, any pair is legal; hence compressing without taking the morphological rules into account can yield a poorer compression ratio. This article suggests a tool that optimizes the Burrows-Wheeler algorithm which is an unaware morphological rules compression method. It first preprocesses a Hebrew text file according to the Hebrew conjugation rules, and, after that, it provides the Burrows-Wheeler algorithm with this preprocessed file so that can be compressed better. Experimental results show a significant improvement.