| 1. | EXECUTIVE SUMMARY | 
| 1.1. | Motivation for emerging image sensor technologies | 
| 1.2. | Report structure | 
| 1.3. | Emerging image sensor technologies included in the report | 
| 1.4. | Comparison with IDTechEx's previous Emerging Image Sensors report | 
| 1.5. | Conventional image sensors: Market overview | 
| 1.6. | Opportunities for SWIR image sensors | 
| 1.7. | Autonomous vehicles will need machine vision | 
| 1.8. | Application readiness level of SWIR detectors | 
| 1.9. | Prospects for QD/OPD-on-CMOS detectors | 
| 1.10. | Challenges for QD-Si technology for SWIR imaging | 
| 1.11. | Future of pulse oximetry could come in the form of flexible skin patches with thin film photodetectors | 
| 1.12. | Applications for hyperspectral imaging | 
| 1.13. | Event-based vision promises reduced data processing and increased dynamic range | 
| 1.14. | Emerging flexible x-ray sensors - Lightweight and low-cost | 
| 1.15. | Miniaturised spectrometers targeting a wide range of sectors | 
| 1.16. | The emergence of quantum image sensing | 
| 1.17. | Emerging image sensors: Key players overview | 
| 1.18. | Emerging image sensors: Key players overview (II) | 
| 1.19. | 10-year market forecast for emerging image sensor technologies | 
| 1.20. | 10-year market forecast for emerging image sensor technologies (by volume) | 
| 1.21. | 10-year market forecast for emerging image sensor technologies (by volume, data table) | 
| 1.22. | 10-year market forecast for emerging image sensor technologies (by market value) | 
| 1.23. | 10-year market forecast for emerging image sensor technologies (by market value, data table) | 
| 1.24. | Key conclusions for emerging image sensors | 
| 2. | INTRODUCTION | 
| 2.1. | Motivation for emerging image sensor technologies | 
| 2.2. | What is a sensor? | 
| 2.3. | Sensor value chain example: Digital camera | 
| 2.4. | Introduction to photodetectors | 
| 2.5. | Working principle of an image sensor | 
| 2.6. | Quantifying photodetector and image sensor performance | 
| 2.7. | Extracting as much information as possible from light | 
| 2.8. | Global autonomous car market | 
| 2.9. | How many cameras needed in different automotive autonomy levels | 
| 2.10. | Increasing usage of drones provides extensive market for emerging image sensors | 
| 2.11. | Emerging image sensors required for drones | 
| 2.12. | Industrial imaging to benefit from integrated hyperspectral "package" solutions | 
| 2.13. | Advanced sensors expected to target consumer electronics | 
| 3. | MARKET FORECASTS | 
| 3.1. | Market forecast methodology | 
| 3.2. | Parametrizing forecast curves | 
| 3.3. | Determining total addressable markets | 
| 3.4. | Determining revenues | 
| 3.5. | 10-year short-wave infra-red (SWIR) image sensors market forecast: By volume | 
| 3.6. | 10-year short-wave infra-red (SWIR) image sensors market forecast: by market value | 
| 3.7. | 10-year short-wave infra-red (SWIR) image sensors market volume forecast data table | 
| 3.8. | 10-year short-wave infra-red (SWIR) image sensors market value forecast data table | 
| 3.9. | 10-year hybrid OPD-on-CMOS image sensors market forecast: by volume | 
| 3.10. | 10-year hybrid OPD-on-CMOS image sensors market forecast: by market value | 
| 3.11. | 10-year hybrid OPD-on-CMOS image sensors market volume forecasts (data table) | 
| 3.12. | 10-year hybrid OPD-on-CMOS image sensors market value forecasts (data table) | 
| 3.13. | 10-year hybrid QD-on-CMOS image sensors market forecast: by volume without consumer electronics | 
| 3.14. | 10-year hybrid QD-on-CMOS image sensors market forecast: by market value without consumer electronics | 
| 3.15. | 10-year hybrid QD-on-CMOS image sensors market volume forecasts (data tables) without consumer electronics | 
| 3.16. | 10-year hybrid QD-on-CMOS image sensors market value forecasts (data tables) without consumer electronics | 
| 3.17. | 10-year hybrid QD-on-CMOS image sensors market forecast: by volume including consumer electronics | 
| 3.18. | 10-year hybrid QD-on-CMOS image sensors market forecast: by value including consumer electronics | 
| 3.19. | 10-year hybrid QD-on-CMOS image sensors market volume forecasts (data tables) with consumer electronics | 
| 3.20. | 10-year hybrid QD-on-CMOS image sensors market value forecasts (data tables) with consumer electronics | 
| 3.21. | 10-year thin film organic and perovskite photodetectors (OPDs and PPDs) market forecast: by volume | 
| 3.22. | 10-year thin film organic and perovskite photodetectors (OPDs and PPDs) market forecast: by value | 
| 3.23. | 10-year thin film organic and perovskite photodetectors (OPDs and PPDs) market volume forecasts (data table) | 
| 3.24. | 10-year thin film organic and perovskite photodetectors (OPDs and PPDs) market value forecasts (data table) | 
| 3.25. | 10-year hyperspectral imaging market forecast: by volume | 
| 3.26. | 10-year hyperspectral imaging market forecast: by value | 
| 3.27. | 10-year hyperspectral imaging market volume forecasts (data table) | 
| 3.28. | 10-year hyperspectral imaging market value forecasts (data table) | 
| 3.29. | 10-year event-based vision market forecast: by volume | 
| 3.30. | 10-year event-based vision market forecast: by value | 
| 3.31. | 10-year event-based vision market volume forecasts (data tables) | 
| 3.32. | 10-year event-based vision market value forecasts (data tables) | 
| 3.33. | 10-year wavefront imaging market forecast: by volume | 
| 3.34. | 10-year wavefront imaging market forecast: by value | 
| 3.35. | 10-year wavefront imaging market volume forecasts (data table) | 
| 3.36. | 10-year wavefront imaging market value forecasts (data table) | 
| 3.37. | 10-year flexible x-ray image sensors market forecast: by volume | 
| 3.38. | 10-year flexible x-ray image sensors market forecast: by value | 
| 3.39. | 10-year miniaturized spectrometers market forecast: by volume | 
| 3.40. | 10-year miniaturized spectrometers market forecast: by market value | 
| 3.41. | 10-year flexible miniaturized spectrometers market volume forecasts (data table) | 
| 3.42. | 10-year flexible miniaturized spectrometers market value forecasts (data table) | 
| 4. | BRIEF OVERVIEW OF ESTABLISHED VISIBLE RANGE IMAGE SENSORS (CCD AND CMOS) | 
| 4.1. | Conventional image sensors: Market overview | 
| 4.2. | Sensor architectures: Front and backside illumination | 
| 4.3. | Key components of an image sensor | 
| 4.4. | Process flow for back-side-illuminated CMOS image sensors | 
| 4.5. | Comparing CMOS and CCD image sensors | 
| 4.6. | Image quality | 
| 4.7. | CCD & CMOS image sensors | 
| 4.8. | What is measured by an image sensor | 
| 4.9. | Benefits of global rather than rolling shutters | 
| 4.10. | Dynamic photodiodes with tuneable sensitivity | 
| 5. | SHORT WAVE INFRARED (SWIR) IMAGE SENSORS | 
| 5.1. | Introduction | 
| 5.1.1. | Electromagnetic spectrum | 
| 5.1.2. | Short-wave infrared spectrum | 
| 5.1.3. | Value propositions of SWIR imaging | 
| 5.1.4. | SWIR imaging reduces light scattering | 
| 5.1.5. | Material choices for infrared sensors | 
| 5.1.6. | Introduction to SWIR detection technologies | 
| 5.1.7. | SWIR imaging: Incumbent and emerging technology options | 
| 5.1.8. | Detectivity benchmarking of emerging image sensor technologies 1 | 
| 5.1.9. | Detectivity benchmarking of emerging image sensor technologies 2 | 
| 5.1.10. | Technology comparison of various image sensor technologies for SWIR imaging | 
| 5.2. | Applications for SWIR Imaging | 
| 5.2.1. | Applications for SWIR imaging | 
| 5.2.2. | SWIR imaging for silicon wafer inspection | 
| 5.2.3. | SWIR imaging for water content identifying | 
| 5.2.4. | SWIR imaging for ADAS and autonomous vehicles | 
| 5.2.5. | SWIR imaging for road condition sensing | 
| 5.2.6. | SWIR imaging for foreign material detection | 
| 5.2.7. | SWIR detection to identify different materials | 
| 5.2.8. | SWIR detection for plastic sorting | 
| 5.2.9. | SWIR imaging for counterfeit detection | 
| 5.2.10. | SWIR imaging for temperature difference measurement | 
| 5.2.11. | SWIR for live animal imaging | 
| 5.2.12. | SWIR imaging for laser profiling and tracking | 
| 5.2.13. | Laser profiling and tracking in medical application | 
| 5.2.14. | Laser profiling and tracking in military and security application | 
| 5.2.15. | SWIR detection for wearable applications | 
| 5.2.16. | Battery inspection using SWIR imaging | 
| 5.2.17. | SWIR sensors: Application overview | 
| 5.2.18. | SWIR QD-on-CMOS imager application summary | 
| 5.2.19. | SWIR image sensing for industrial process optimization | 
| 5.2.20. | Industrial imaging is a growing market for SWIR sensors | 
| 5.2.21. | MULTIPLE (EU Project): Focus areas, targets and participants | 
| 5.2.22. | SWIR image sensors for hyperspectral imaging | 
| 5.2.23. | SWIR application requirements | 
| 5.2.24. | Key takeaways: SWIR Applications | 
| 5.3. | InGaAs Sensors - Existing Technology for SWIR Imaging | 
| 5.3.1. | InGaAs for incumbent image sensors | 
| 5.3.2. | InGaAs sensor design: Solder bumps limit resolution | 
| 5.3.3. | Sony improve InGaAs sensor resolution and spectral range | 
| 5.3.4. | What makes InGaAs sensors expensive? | 
| 5.3.5. | The challenge of high resolution and low-cost IR sensors | 
| 5.3.6. | Key takeaways: InGaAs sensors | 
| 5.4. | Emerging Inorganic SWIR Technologies and Players | 
| 5.4.1. | Extended range silicon can be achieved through internal photoemission | 
| 5.4.2. | TriEye commercialising low-cost extended silicon SWIR sensors | 
| 5.4.3. | Increasing silicon CMOS sensitivity at the band edge | 
| 5.4.4. | OmniVision: Making silicon CMOS sensitive to NIR | 
| 5.4.5. | Germanium SWIR sensors are just now available | 
| 5.4.6. | SWOT analysis: SWIR image sensors (non-hybrid, non-InGaAs) | 
| 5.4.7. | Key players in the SWIR sensor market (monolithic, non-InGaAs) | 
| 5.4.8. | Key takeaways: Detecting SWIR with silicon | 
| 6. | HYBRID OPD-ON-CMOS IMAGE SENSORS (INCLUDING SWIR) | 
| 6.1. | OPD-on-CMOS hybrid image sensors | 
| 6.2. | Panasonic postponed launch of OPD-on-CMOS broadcast cameras | 
| 6.3. | Fraunhofer developing affordable OPD-on-CMOS sensors | 
| 6.4. | Fraunhofer's OPD-on-CMOS SWIR sensor architecture | 
| 6.5. | Twisted bilayer graphene sensitive to longer wavelength IR light | 
| 6.6. | Technology readiness level of OPD-on-CMOS detectors by application | 
| 6.7. | SWOT analysis of OPD-on-CMOS image sensors | 
| 6.8. | Supplier overview: OPD-on-CMOS hybrid image sensors | 
| 6.9. | Key takeaways: Hybrid OPD on CMOS | 
| 7. | HYBRID QD-ON-CMOS IMAGE SENSORS | 
| 7.1. | Introduction to Hybrid QD-on-CMOS Image Sensors | 
| 7.1.1. | Quantum dots absorption dependence: Size | 
| 7.1.2. | Quantum dots absorption dependence: Materials | 
| 7.1.3. | Quantum dots: PbS | 
| 7.1.4. | Types of commercial QD sensor arrays | 
| 7.1.5. | Hybrid QD-on-CMOS image sensor architecture | 
| 7.1.6. | QD-on-CMOS pixelation | 
| 7.1.7. | Manufacturing of QD-on-CMOS | 
| 7.1.8. | QD-on-CMOS fabrication processes | 
| 7.1.9. | Solution processing techniques | 
| 7.1.10. | QD-on-CMOS: From solution to photodiode | 
| 7.1.11. | Business model for producing QD-on-CMOS sensors | 
| 7.1.12. | QD optical layer: Approaches to increase conductivity of QD films | 
| 7.1.13. | Required performance level of SWIR image sensors used for ADAS / autonomous vehicles | 
| 7.1.14. | Challenges for QD-Si technology for SWIR imaging | 
| 7.1.15. | Pixel pitch evolution | 
| 7.1.16. | Alternative QDs | 
| 7.2. | QD Image Sensor for Visible Spectra | 
| 7.2.1. | QD-Si hybrid image sensors: Increased sensitivity and reduced thickness | 
| 7.2.2. | TFPD vs Si PD | 
| 7.2.3. | QD-Si hybrid image sensors: Enabling high resolution global shutter | 
| 7.2.4. | Global shutter image sensor comparison | 
| 7.3. | QD Image Sensor for UV Imaging | 
| 7.3.1. | Motivation | 
| 7.3.2. | QD can improve sensitivity in the UV region | 
| 7.3.3. | Integration with the image sensors | 
| 7.3.4. | Perovskite QDs for UV sensors | 
| 7.3.5. | QD-on-CMOS for UV imaging is emerging | 
| 7.3.6. | Potential applications | 
| 7.4. | Case Studies of Hybrid QD-on-CMOS Image Sensors | 
| 7.4.1. | Hybrid QD-on-CMOS with global shutter for SWIR imaging | 
| 7.4.2. | Early efforts from RTI International | 
| 7.4.3. | SWIR Vision Systems' 2-layer QD system | 
| 7.4.4. | SWIR Vision Systems' CQD photodetectors | 
| 7.4.5. | Emberion's VS20 VIS-SWIR camera | 
| 7.4.6. | Emberion's QD-graphene SWIR photoconductor | 
| 7.4.7. | ST Microelectronic's QD image sensor technology | 
| 7.4.8. | ST Microelectronic's QD image sensor technology | 
| 7.4.9. | ICFO's graphene/QD image sensor | 
| 7.4.10. | Wide spectrum image sensor enabled by Qurv Technologies | 
| 7.4.11. | Imec's TFPD image sensor | 
| 7.4.12. | IMEC outline QD-on-CMOS architecture roadmap | 
| 7.4.13. | Applications for QD-on-CMOS image sensors | 
| 7.4.14. | Pixel engine improvement to increase SNR | 
| 7.4.15. | Specs of existing QD-on-CMOS image sensors | 
| 8. | THIN FILM PHOTODETECTORS (ORGANIC AND PEROVSKITE) | 
| 8.1. | Overview | 
| 8.1.1. | Introduction to thin film photodetectors (organic and perovskite) | 
| 8.1.2. | Organic photodetectors (OPDs) | 
| 8.1.3. | Thin film photodetectors: Advantages and disadvantages | 
| 8.1.4. | Reducing dark current to increase dynamic range | 
| 8.1.5. | Tailoring the detection wavelength to specific applications | 
| 8.1.6. | Extending OPDs to the NIR region: Use of cavities | 
| 8.1.7. | Technical challenges for manufacturing thin film photodetectors from solution | 
| 8.1.8. | Materials for thin film photodetectors | 
| 8.2. | Thin Film Photodetectors: Applications and Key Players | 
| 8.2.1. | Applications of organic photodetectors | 
| 8.2.2. | OPDs for biometric security | 
| 8.2.3. | Spray-coated organic photodiodes for medical imaging | 
| 8.2.4. | ISORG develops fingerprint-on-display with OPDs | 
| 8.2.5. | Flexible OPD imaging applications with a TFT active-matrix backplane | 
| 8.2.6. | First OPD production line | 
| 8.2.7. | Future of pulse oximetry could come in the form of flexible skin patches with organic photodetectors | 
| 8.2.8. | Perovskite based image sensors offer high dynamic range | 
| 8.2.9. | Commercial challenges for large-area OPD adoption | 
| 8.2.10. | Technical requirements for thin film photodetector applications | 
| 8.2.11. | Thin-film OPD and PPD application requirements | 
| 8.2.12. | Application assessment for thin film OPDs and PPDs | 
| 8.2.13. | Technology readiness level of organic and perovskite photodetectors by applications | 
| 8.2.14. | SWOT analysis of large area OPD image sensors | 
| 8.2.15. | Key takeaways: Thin film photodetectors | 
| 9. | HYPERSPECTRAL IMAGING | 
| 9.1. | Overview | 
| 9.1.1. | Introduction to hyperspectral imaging | 
| 9.1.2. | Multiple methods to acquire a hyperspectral data-cube | 
| 9.1.3. | Contrasting device architectures for hyperspectral data acquisition | 
| 9.1.4. | Line-scan (push-broom) cameras ideal for conveyor belts and satellite images | 
| 9.1.5. | Comparison between 'push-broom' and older hyperspectral imaging methods | 
| 9.1.6. | Line-scan hyperspectral camera design | 
| 9.1.7. | Snapshot hyperspectral imaging | 
| 9.1.8. | Illumination for hyperspectral imaging | 
| 9.1.9. | Pansharpening for multi/hyper-spectral image enhancement | 
| 9.1.10. | Hyperspectral imaging as a development of multispectral imaging | 
| 9.1.11. | Trade-offs between hyperspectral and multi spectral imaging | 
| 9.1.12. | High-throughput hyperspectral imaging without image degradation | 
| 9.1.13. | Towards broadband hyperspectral imaging | 
| 9.2. | Applications of Hyperspectral Imaging | 
| 9.2.1. | Applications of hyperspectral imaging | 
| 9.2.2. | Encouraging adoption of hyperspectral imaging in a production environment | 
| 9.2.3. | Hyperspectral imaging and precision agriculture | 
| 9.2.4. | Hyperspectral imaging for UAVs (drones) | 
| 9.2.5. | Agricultural drones ecosystem develops | 
| 9.2.6. | Satellite imaging with hyperspectral cameras | 
| 9.2.7. | Historic drone investment creates demand for hyperspectral imaging | 
| 9.2.8. | In-line inspection with hyperspectral imaging | 
| 9.2.9. | Object identification with in-line hyperspectral imaging | 
| 9.2.10. | Distinguishing materials from spectral differences | 
| 9.2.11. | Sorting objects for recycling with hyperspectral imaging | 
| 9.2.12. | Food inspection with hyperspectral imaging | 
| 9.2.13. | Hyperspectral imaging for skin diagnostics | 
| 9.2.14. | Hyperspectral imaging application requirements | 
| 9.2.15. | Hyperspectral imaging - Barriers to entry | 
| 9.2.16. | SWOT analysis: Hyperspectral imaging | 
| 9.3. | Hyperspectral Imaging: Key Players | 
| 9.3.1. | Specim: Market leaders in line-scan imaging | 
| 9.3.2. | Headwall Photonics providing integrated software solutions | 
| 9.3.3. | Resonon Inc: High-throughput hyperspectral imaging without image degradation | 
| 9.3.4. | Cubert: Specialists in snapshot spectral imaging | 
| 9.3.5. | Wavelength ranges vary by manufacturer | 
| 9.3.6. | Hyperspectral wavelength range vs spectral resolution | 
| 9.3.7. | Hyperspectral camera parameter table | 
| 9.3.8. | Condi Food: Food quality monitoring with hyperspectral imaging | 
| 9.3.9. | Orbital Sidekick: Hyperspectral imaging from satellites | 
| 9.3.10. | Gamaya: Hyperspectral imaging for agricultural analysis | 
| 9.3.11. | Telops: Infrared hyperspectral imaging for gas sensing | 
| 9.3.12. | Telops: Mapping gas distribution from airborne hyperspectral cameras | 
| 9.3.13. | Key players in hyperspectral imaging | 
| 9.3.14. | Key takeaways: Hyperspectral imaging | 
| 10. | MINIATURIZED SPECTROSCOPY | 
| 10.1. | Introduction: Miniaturized spectrometers | 
| 10.2. | Conventional diffractive optics - Lower resolution with decreasing spectrometer size | 
| 10.3. | SWOT analysis: Diffractive optics | 
| 10.4. | Filter arrays can enable more compact spectrometer designs with higher resolution | 
| 10.5. | SWOT analysis: Filter arrays | 
| 10.6. | Reconstructive spectroscopy is an emerging technique | 
| 10.7. | SWOT analysis: Reconstructive spectroscopy | 
| 10.8. | Miniaturised spectrometers targeting a wide range of sectors | 
| 10.9. | Minimum specification varies widely depending on application | 
| 10.10. | Consumer electronics could be a growing market for mini-spectrometers | 
| 10.11. | High spectral resolution enabled on CMOS sensors | 
| 10.12. | Photonic crystals as a dispersive element | 
| 10.13. | Key players in mini-spectrometry | 
| 10.14. | Resolution and cost are key differentiators among key players | 
| 10.15. | Key takeaways: Miniaturised spectroscopy | 
| 11. | EVENT-BASED VISION | 
| 11.1. | Introduction | 
| 11.1.1. | What is event-based sensing? | 
| 11.1.2. | General event-based sensing: Pros and cons | 
| 11.1.3. | What is event-based vision? 1 | 
| 11.1.4. | What is event-based vision? 2 | 
| 11.1.5. | What does event-based vision data look like? | 
| 11.1.6. | Event-based vision: Pros and cons | 
| 11.1.7. | Event-based vision sensors enable increased dynamic range | 
| 11.1.8. | Cost and software of event-based sensors | 
| 11.2. | Applications of Event-Based Vision | 
| 11.2.1. | Promising applications for event-based vision | 
| 11.2.2. | Event-based vision for autonomous vehicles | 
| 11.2.3. | Event-based vision for unmanned ariel vehicle (UAV) collision avoidance | 
| 11.2.4. | Occupant tracking (fall detection) in smart buildings | 
| 11.2.5. | Event-based vision for augmented/virtual reality | 
| 11.2.6. | Event-based vision for optical alignment/beam profiling | 
| 11.2.7. | Event-based vision application requirements | 
| 11.2.8. | Technology readiness level of event-based vision by application | 
| 11.3. | Event-based Vision: Key Players | 
| 11.3.1. | Event-based vision: Company landscape | 
| 11.3.2. | IniVation: Aiming for organic growth | 
| 11.3.3. | Prophesee: Well-funded and targeting autonomous mobility | 
| 11.3.4. | Smaller companies being acquired by household names | 
| 11.3.5. | Sony has gone to production with smallest pixel event-based sensor | 
| 11.3.6. | SWOT analysis: Event-based vision | 
| 11.3.7. | Key players in event-based vision | 
| 11.3.8. | Key takeaways: Event-based vision | 
| 12. | WAVEFRONT (PHASE) IMAGING | 
| 12.1. | Motivation for wavefront imaging | 
| 12.2. | Conventional Shack-Hartman wavefront sensors | 
| 12.3. | Applications of wavefront imaging | 
| 12.4. | Phasics: Innovators in wavefront imaging | 
| 12.5. | Wooptix: Light-field and wavefront imaging | 
| 12.6. | SWOT analysis: Wavefront imaging | 
| 12.7. | Key takeaways: Wavefront imaging | 
| 13. | FLEXIBLE AND DIRECT X-RAY IMAGE SENSORS | 
| 13.1. | Conventional x-ray sensing | 
| 13.2. | Flexible x-ray image sensors based on amorphous-Si | 
| 13.3. | Spray-coated organic photodiodes for medical imaging | 
| 13.4. | Direct x-ray sensing with organic semiconductors | 
| 13.5. | Holst Centre develop perovskite-based x-ray sensors 1 | 
| 13.6. | Holst Centre develop perovskite-based x-ray sensors 2 | 
| 13.7. | Siemens Healthineers: Direct x-ray sensing with perovskites 1 | 
| 13.8. | Siemens Healthineers: Direct x-ray sensing with perovskites 2 | 
| 13.9. | Technology readiness level of flexible and direct x-ray sensors | 
| 13.10. | SWOT analysis: Flexible and direct x-ray image sensors | 
| 13.11. | Key takeaways: Flexible x-ray sensors | 
| 14. | QUANTUM IMAGE SENSORS | 
| 14.1. | Introduction: Quantum image sensors | 
| 14.2. | Fraunhofer exploring quantum ghost imaging | 
| 14.3. | Dartmouth University: Binary quanta image sensors (QIS) | 
| 14.4. | Gigajot commercialising quanta image sensors | 
| 14.5. | Scalable quanta image sensors | 
| 14.6. | SWOT analysis: Quantum image sensing | 
| 14.7. | Key takeaways: Quantum image sensors | 
| 15. | COMPUTER VISION | 
| 15.1. | Computer vision is segmented into 3R's | 
| 15.2. | Recognition, registration and reconstruction | 
| 15.3. | Sliding window algorithm - a modern foundation to computer vision | 
| 15.4. | Feature extraction mechanisms - pixel-based approach | 
| 15.5. | Feature extraction mechanisms - color-based approach | 
| 15.6. | Feature extraction mechanisms - gradient-based approach | 
| 15.7. | Using Histogram of Oriented Gradients to find people and objects in images | 
| 15.8. | From artificial intelligence, to machine learning and deep learning | 
| 15.9. | Artificial intelligence in the development of human-machine interactions | 
| 15.10. | Terminologies and scopes | 
| 15.11. | Sub-technology of computer vision | 
| 15.12. | Computers can recognize objects better than humans for the first time | 
| 15.13. | Computers interpret an image in a different way | 
| 15.14. | Image recognition by convolutional neural networks | 
| 15.15. | Object detection | 
| 16. | COMPANY PROFILES | 
| 16.1. | Brilliant Matters | 
| 16.2. | Condi Food | 
| 16.3. | Cubert | 
| 16.4. | DpiX | 
| 16.5. | Emberion | 
| 16.6. | Fraunhofer | 
| 16.7. | Gamaya | 
| 16.8. | Headwall | 
| 16.9. | Holst Centre | 
| 16.10. | imec | 
| 16.11. | IniVation | 
| 16.12. | ISORG | 
| 16.13. | Omnivision | 
| 16.14. | Orbital Sidekick | 
| 16.15. | Panasonic | 
| 16.16. | Phasics | 
| 16.17. | Prophesee | 
| 16.18. | Qurv | 
| 16.19. | Siemens Healthineers | 
| 16.20. | Specim | 
| 16.21. | Spectricity | 
| 16.22. | Stratio | 
| 16.23. | SWIR Vision Systems | 
| 16.24. | TriEye | 
| 16.25. | Wooptix |