Devices that work on this technology usually follow these stages but their duration might vary from machine to machine depending on its configuration and the task it is supposed to do. A basic working of the gesture sensors and recognition system can be understood from the following figure:
The gesture system is divided into three independent modules. The three all can control the robot independently and realize the recognition of different gestures effectively. Modules include “wave” mode, “virtual button” mode and “glove” mode. With different processing modules as the main body, the detailed information of the gesture is obtained through the recognition algorithm, which can be judged according to the characteristics, and finally the type of the input gesture is obtained.
APDS-9960 Gesture Sensors:
The APDS-9960 is a serious little piece of hardware with built in UV and IR blocking filters, four separate diodes sensitive to different directions, and an I2C compatible interface. For your convenience we have broken out the following pins: VL (optional power to IR LED), GND (Ground), VCC (power to APDS-9960 sensor), SDA (I2C data), SCL (I2C clock), and INT (interrupt). Each APDS-9960 also has a detection range of 4 to 8 inches (10 to 20 cm).
- Sensing, and Gesture Detection in an Optical Module
- Ambient Light and RGB Color Sensing
- UV and IR blocking filters
- Programmable gain and integration time
- Very high sensitivity – Ideally suited for operation behind dark glass
- Proximity Sensing
- Trimmed to provide consistent reading
- Ambient light rejection
- Offset compensation
- Programmable driver for IR LED current
- Saturation indicator bit
- Complex Gesture Sensing
- Four separate diodes sensitive to different directions
- Ambient light rejection
- Offset compensation
- Programmable driver for IR LED current
- 32 dataset storage FIFO
- Interrupt driven I2C communication
- I2C-bus Fast Mode Compatible Interface
- Data Rates up to 400kHz
- Dedicated Interrupt Pin
- Small Package L3.94 × W2.36 × H1.35mm
Application of this sensor is limited for LEFT, RIGHT , UP and DOWN directions. And sensor is able to detect upto 20cm only.
Check this video which has detected direction of hand movement. APDS-9960 is interfaced with PIC controller.
VCNL4035X01 Gesture sensors:
Fully Integrated Proximity and Ambient Light Sensor With I2C Interface and Interrupt Function for Gesture Applications.
FEATURES
- Package type: surface-mount
- Dimensions (L x W x H in mm): 4.0 x 2.36 x 0.75
- AEC-Q101 qualified
- Integrated modules: ambient light sensor (ALS), proximity sensor (PS), and signal conditioning ICL Operates ALS and PS in parallel structure
- FiltronTM technology adoption for robust background light cancellation
- Temperature compensation: -40 °C to +105 °C
- Low power consumption I2C (SMBus compatible) interface
- Output type: I2C bus (ALS / PS)
- Operation voltage: 2.5 V to 3.6 V
- Floor life: 168 h, MSL 3, according to J-STD-020
VCNL4035X01 allows to connect up to 3 external IREDs. Each may be selected separate to allow for normal proximity.
VCNL4035X01 integrates a proximity sensor (PS), ambient light sensor (ALS), a muxx, and a driver for up to 3 external IREDs / LEDs into one small package.
For detail information regarding this sensor refer datasheet.
Two Methods for Gesture sensors Analysis:
1. Position-based Method Advantages and Drawbacks
The advantage of the position-based method over phase-based is that the position-based method can offer information on the location of the target. This will allow for ratiometric control of systems. For example, to scroll through a book several pages you could suspend your hand over the right side of the detectable area instead of having to make several right swipe gestures. The main drawback of the position-based algorithm is the accuracy of the position calculations.
The positioning algorithm assumes a spherical output from the LEDs, but in practice LED output is more conical than spherical. The algorithm also assumes uniform light intensity across the entire output of the LED, but the light intensity decays away from the normal. Another issue is that this algorithm does not account for the shape of the target. A target that is uniquely shaped will cause inconsistencies with the positioning output. For example, the system cannot tell the difference between the hand and the wrist, so any gestures involving movement that puts the wrist in the area of detection will be less accurately located.
The result is that the positioning information provided in this algorithm is good enough for low resolution systems that only need a 3×3 grid of detection, but the current positioning algorithm is not well-suited for a pointing application. This algorithm’s output is not an ideal touchscreen replacement.
2. Phase-based Method Advantages and Drawbacks
For applications not requiring position information, the phase-based method provides a very robust way of detecting gestures. Each gesture can be detected on either the entry or exit from the detectable area, and the entry and exit can be double-checked with each other to provide much higher certainty for each gesture observed. The drawback of this method when compared with the position-based method is that no positioning information is provided. This means that the number of gestures that can be implemented are more limited than the position based method. The phase-based method can only tell the direction of entry and exit from the detectable area so any movement in the middle of the detectable area is not detected.
There is very useful document of Silicon Labs gives proper understanding for developer to develop algorithms for such type of gesture.